First Push

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c5a0ae242b4134f17872ed219d6f089c3cef7011eb5a73ff4db61eefb0dfa13
+oid sha256:4f8667131df6e196b3ed33ff13c02165dfe19b3b3483ec7601f420365bbdfb7b
 size 1764633

SoccerTwos/SoccerTwos-499020.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07cbe648d142f8a828cd69b18a427a27d92bbbb844e7e1cf78284a049f5be1e3
+size 1764633

SoccerTwos/SoccerTwos-499020.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d072ddaa5bbf139e3209efab264a4d8ecaeb92a7abc6aef7fe8aa84fc07e4b0
+size 28421201

SoccerTwos/SoccerTwos-499840.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f777b81271426f55e48cfda92df6dff01d711f03e6a9147f503905aade116b8
+size 1764633

SoccerTwos/SoccerTwos-499840.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53d82d463973507ac0b560b78c0d40f0496d4beefc2255909d0c2e8b77b72b78
+size 28421201

SoccerTwos/SoccerTwos-522784.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f8667131df6e196b3ed33ff13c02165dfe19b3b3483ec7601f420365bbdfb7b
+size 1764633

SoccerTwos/SoccerTwos-522784.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0922efabd86c24784b45ef4ca95cb31bcad68531ef1ae7e385e1053d335b0a06
+size 28421201

SoccerTwos/SoccerTwos-992740.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c2e0ae05ce3ed60c622a69ae379a803fbae04eabfdd957b02a2c19a0be5310f
+size 1764633

SoccerTwos/SoccerTwos-992740.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c71a519e3a503d7d56a1beb3415915644801a151aadd906098a2de11a5231747
+size 28421201

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01066a58dfc3a8cb6c8523df90983ae20d21958e858114f3f900a2edc2c1c59d
+oid sha256:0922efabd86c24784b45ef4ca95cb31bcad68531ef1ae7e385e1053d335b0a06
 size 28421201

SoccerTwos/{events.out.tfevents.1680447936.b960f9b6847a.20737.0 → events.out.tfevents.1680463250.b960f9b6847a.84812.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5d736a7b7379219448851c5346603b062cdfbfe44dc65da51349b6523820a49
-size 545912
+oid sha256:3ddf49668196e408000d5f2d00a1bdb3fb9c24bc0016a58a2b46a94e5636f5c6
+size 256484

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 256, "buffer_size": 51200, "learning_rate": 0.001, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 5000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 4000, "window": 10, "play_against_latest_model_ratio": 0.3, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos/SoccerTwos", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 1024, "buffer_size": 10240, "learning_rate": 3e-05, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 1000, "summary_freq": 20000, "threaded": false, "self_play": {"save_steps": 200000, "team_change": 200000, "swap_steps": 200000, "window": 3, "play_against_latest_model_ratio": 0.001, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos/SoccerTwos", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -3,16 +3,16 @@ behaviors:
   SoccerTwos:
     trainer_type: poca
     hyperparameters:
-      batch_size: 256
-      buffer_size: 51200
-      learning_rate: 0.001
+      batch_size: 1024
+      buffer_size: 10240
+      learning_rate: 3.0e-05
       beta: 0.005
       epsilon: 0.2
       lambd: 0.95
       num_epoch: 3
-      learning_rate_schedule: linear
-      beta_schedule: linear
-      epsilon_schedule: linear
+      learning_rate_schedule: constant
+      beta_schedule: constant
+      epsilon_schedule: constant
     checkpoint_interval: 500000
     network_settings:
       normalize: false
@@ -37,16 +37,16 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 5000000
+    max_steps: 1000000
     time_horizon: 1000
-    summary_freq: 10000
+    summary_freq: 20000
     threaded: false
     self_play:
-      save_steps: 50000
+      save_steps: 200000
       team_change: 200000
-      swap_steps: 4000
-      window: 10
-      play_against_latest_model_ratio: 0.3
+      swap_steps: 200000
+      window: 3
+      play_against_latest_model_ratio: 0.001
       initial_elo: 1200.0
     behavioral_cloning: null
 env_settings:

run_logs/Player-0.log

@@ -31,7 +31,7 @@ ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.105 seconds
+- Completed reload, in  0.164 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -56,7 +56,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 1.163528 ms
+UnloadTime: 1.389530 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
@@ -272,66 +272,12 @@ TOO LONG
 TOO LONG
 TOO LONG
 TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
 Setting up 1 worker threads for Enlighten.
 Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 13293 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 10145 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.1 MB
@@ -453,16 +399,16 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 13294 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 10146 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 4.6 MB
+      Peak Allocated memory 5.1 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 13294 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 10146 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.6 MB
+      Peak Allocated memory 17.1 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -491,13 +437,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 13293 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 10145 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 65.6 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [128.0 KB-256.0 KB]: 13294 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 10146 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -509,13 +455,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 13294 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 10146 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 0.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 13293 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 10145 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.4 MB
@@ -527,13 +473,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 13294 frames
+      Peak usage frame count: [0-1.0 KB]: 10146 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 13293 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 10145 frames, [2.0 KB-4.0 KB]: 1 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 KB

run_logs/timers.json

@@ -2,201 +2,201 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 3.176081418991089,
-            "min": 3.1186532974243164,
-            "max": 3.295772075653076,
-            "count": 68
+            "value": 3.2872567176818848,
+            "min": 3.286691188812256,
+            "max": 3.29567813873291,
+            "count": 26
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 92385.859375,
-            "min": 27188.6171875,
-            "max": 125493.28125,
-            "count": 68
+            "value": 124652.7734375,
+            "min": 105414.2265625,
+            "max": 192239.484375,
+            "count": 26
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 866.0,
-            "min": 471.3636363636364,
+            "value": 864.1666666666666,
+            "min": 548.5263157894736,
             "max": 999.0,
-            "count": 68
+            "count": 26
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 20784.0,
-            "min": 14536.0,
-            "max": 25920.0,
-            "count": 68
+            "value": 41480.0,
+            "min": 36396.0,
+            "max": 43624.0,
+            "count": 26
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1199.0819742273839,
-            "min": 1196.117497819503,
-            "max": 1212.9964846267926,
-            "count": 60
+            "value": 1218.8468970466909,
+            "min": 1199.970658184939,
+            "max": 1220.4868010648804,
+            "count": 25
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 2398.1639484547677,
-            "min": 2393.734714572937,
-            "max": 19404.71771389773,
-            "count": 60
+            "value": 7313.081382280145,
+            "min": 4849.203257003486,
+            "max": 21799.100644154005,
+            "count": 25
         },
         "SoccerTwos.Step.mean": {
-            "value": 679414.0,
-            "min": 9980.0,
-            "max": 679414.0,
-            "count": 68
+            "value": 519896.0,
+            "min": 19842.0,
+            "max": 519896.0,
+            "count": 26
         },
         "SoccerTwos.Step.sum": {
-            "value": 679414.0,
-            "min": 9980.0,
-            "max": 679414.0,
-            "count": 68
+            "value": 519896.0,
+            "min": 19842.0,
+            "max": 519896.0,
+            "count": 26
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.0014615395339205861,
-            "min": -0.003923033829778433,
-            "max": 0.09618460386991501,
-            "count": 68
+            "value": 0.002666894346475601,
+            "min": -0.016579050570726395,
+            "max": 0.026599397882819176,
+            "count": 26
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -0.01753847487270832,
-            "min": -0.08733416348695755,
-            "max": 1.6351382732391357,
-            "count": 68
+            "value": 0.06400546431541443,
+            "min": -0.39789721369743347,
+            "max": 0.7181837558746338,
+            "count": 26
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.0010113714961335063,
-            "min": -0.0015273918397724628,
-            "max": 0.0961824581027031,
-            "count": 68
+            "value": 0.0027757426723837852,
+            "min": -0.016334908083081245,
+            "max": 0.025997892022132874,
+            "count": 26
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -0.012136457487940788,
-            "min": -0.03370322659611702,
-            "max": 1.635025143623352,
-            "count": 68
+            "value": 0.06661782413721085,
+            "min": -0.3920377790927887,
+            "max": 0.7019430994987488,
+            "count": 26
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 68
+            "count": 26
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 68
+            "count": 26
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": 0.13293332854906717,
-            "min": -0.5384615384615384,
-            "max": 0.2183076968559852,
-            "count": 68
+            "value": -0.018300001199046772,
+            "min": -0.2450000001117587,
+            "max": 0.16351666465440454,
+            "count": 26
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": 1.5951999425888062,
-            "min": -7.0,
-            "max": 3.456799954175949,
-            "count": 68
+            "value": -0.4392000287771225,
+            "min": -6.177600026130676,
+            "max": 4.148799955844879,
+            "count": 26
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": 0.13293332854906717,
-            "min": -0.5384615384615384,
-            "max": 0.2183076968559852,
-            "count": 68
+            "value": -0.018300001199046772,
+            "min": -0.2450000001117587,
+            "max": 0.16351666465440454,
+            "count": 26
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": 1.5951999425888062,
-            "min": -7.0,
-            "max": 3.456799954175949,
-            "count": 68
-        },
-        "SoccerTwos.IsTraining.mean": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 68
-        },
-        "SoccerTwos.IsTraining.sum": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 68
+            "value": -0.4392000287771225,
+            "min": -6.177600026130676,
+            "max": 4.148799955844879,
+            "count": 26
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.04508198902305865,
-            "min": 0.04508198902305865,
-            "max": 0.05027211560680522,
-            "count": 13
+            "value": 0.024802533712830734,
+            "min": 0.019210267604042503,
+            "max": 0.028650288448746626,
+            "count": 26
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.04508198902305865,
-            "min": 0.04508198902305865,
-            "max": 0.05027211560680522,
-            "count": 13
+            "value": 0.04960506742566147,
+            "min": 0.019210267604042503,
+            "max": 0.05730057689749325,
+            "count": 26
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.0016590526641937563,
-            "min": 0.0016590526641937563,
-            "max": 0.006228569118505777,
-            "count": 13
+            "value": 0.001178079457189817,
+            "min": 0.0006265422296178947,
+            "max": 0.004788236855176475,
+            "count": 26
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.0016590526641937563,
-            "min": 0.0016590526641937563,
-            "max": 0.006228569118505777,
-            "count": 13
+            "value": 0.002356158914379634,
+            "min": 0.0012530844592357894,
+            "max": 0.00957647371035295,
+            "count": 26
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.0016599054455130715,
-            "min": 0.0016599054455130715,
-            "max": 0.005223671512386459,
-            "count": 13
+            "value": 0.0011812268988278722,
+            "min": 0.0006290865095996362,
+            "max": 0.004796333432508012,
+            "count": 26
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.0016599054455130715,
-            "min": 0.0016599054455130715,
-            "max": 0.005223671512386459,
-            "count": 13
+            "value": 0.0023624537976557444,
+            "min": 0.0012581730191992724,
+            "max": 0.009592666865016024,
+            "count": 26
         },
         "SoccerTwos.Policy.LearningRate.mean": {
-            "value": 0.00086431721356828,
-            "min": 0.00086431721356828,
-            "max": 0.00098956480104352,
-            "count": 13
+            "value": 2.9999999999999997e-05,
+            "min": 2.9999999999999994e-05,
+            "max": 3.000000000000001e-05,
+            "count": 26
         },
         "SoccerTwos.Policy.LearningRate.sum": {
-            "value": 0.00086431721356828,
-            "min": 0.00086431721356828,
-            "max": 0.00098956480104352,
-            "count": 13
+            "value": 5.9999999999999995e-05,
+            "min": 2.9999999999999994e-05,
+            "max": 6e-05,
+            "count": 26
         },
         "SoccerTwos.Policy.Epsilon.mean": {
-            "value": 0.18643172000000005,
-            "min": 0.18643172000000005,
-            "max": 0.19895648000000007,
-            "count": 13
+            "value": 0.20000000000000004,
+            "min": 0.19999999999999998,
+            "max": 0.20000000000000007,
+            "count": 26
         },
         "SoccerTwos.Policy.Epsilon.sum": {
-            "value": 0.18643172000000005,
-            "min": 0.18643172000000005,
-            "max": 0.19895648000000007,
-            "count": 13
+            "value": 0.4000000000000001,
+            "min": 0.19999999999999998,
+            "max": 0.40000000000000013,
+            "count": 26
         },
         "SoccerTwos.Policy.Beta.mean": {
-            "value": 0.004322942827999998,
-            "min": 0.004322942827999998,
-            "max": 0.004947928352,
-            "count": 13
+            "value": 0.005000000000000001,
+            "min": 0.005,
+            "max": 0.005000000000000001,
+            "count": 26
         },
         "SoccerTwos.Policy.Beta.sum": {
-            "value": 0.004322942827999998,
-            "min": 0.004322942827999998,
-            "max": 0.004947928352,
-            "count": 13
+            "value": 0.010000000000000002,
+            "min": 0.005,
+            "max": 0.010000000000000002,
+            "count": 26
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 26
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 26
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1680447935",
+        "start_time_seconds": "1680463249",
         "python_version": "3.9.16 (main, Dec  7 2022, 01:11:51) \n[GCC 9.4.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos --run-id=SoccerTwos --no-graphics --force",
         "mlagents_version": "0.31.0.dev0",
@@ -204,59 +204,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1680456446"
+        "end_time_seconds": "1680466520"
     },
-    "total": 8511.370874711,
+    "total": 3271.2702342910015,
     "count": 1,
-    "self": 0.2736131790006766,
+    "self": 0.07394331200339366,
     "children": {
         "run_training.setup": {
-            "total": 0.14687061499989795,
+            "total": 0.1390552890006802,
             "count": 1,
-            "self": 0.14687061499989795
+            "self": 0.1390552890006802
         },
         "TrainerController.start_learning": {
-            "total": 8510.950390916998,
+            "total": 3271.0572356899975,
             "count": 1,
-            "self": 2.1310844998515677,
+            "self": 1.6023544630952529,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 1.647580370000469,
-                    "count": 4,
-                    "self": 1.647580370000469
+                    "total": 1.8770540440018522,
+                    "count": 3,
+                    "self": 1.8770540440018522
                 },
                 "TrainerController.advance": {
-                    "total": 8506.702014102148,
-                    "count": 44654,
-                    "self": 2.4075724592603365,
+                    "total": 3267.1234863749014,
+                    "count": 34068,
+                    "self": 1.7454869784523908,
                     "children": {
                         "env_step": {
-                            "total": 1735.4480031808644,
-                            "count": 44654,
-                            "self": 1436.8803736658,
+                            "total": 1310.969112772931,
+                            "count": 34068,
+                            "self": 1084.5959568313629,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 297.2541033298903,
-                                    "count": 44654,
-                                    "self": 13.094140013877222,
+                                    "total": 225.32441465809097,
+                                    "count": 34068,
+                                    "self": 9.370919056407729,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 284.1599633160131,
-                                            "count": 88624,
-                                            "self": 284.1599633160131
+                                            "total": 215.95349560168324,
+                                            "count": 67640,
+                                            "self": 215.95349560168324
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.3135261851739415,
-                                    "count": 44653,
+                                    "total": 1.048741283477284,
+                                    "count": 34067,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 8497.724515322912,
-                                            "count": 44653,
+                                            "total": 3260.8311980583057,
+                                            "count": 34067,
                                             "is_parallel": true,
-                                            "self": 7329.078901917885,
+                                            "self": 2369.2416122215473,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0034158999997089268,
+                                                            "total": 0.007107666999218054,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.0008994400022857008,
+                                                            "self": 0.0013040509984421078,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.002516459997423226,
+                                                                    "total": 0.005803616000775946,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.002516459997423226
+                                                                    "self": 0.005803616000775946
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.05621618599980138,
+                                                            "total": 0.117101977000857,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0013311599996086443,
+                                                            "self": 0.0014182319973770063,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0006481760001406656,
+                                                                    "total": 0.0011051840010622982,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0006481760001406656
+                                                                    "self": 0.0011051840010622982
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.05018758699952741,
+                                                                    "total": 0.1028438780012948,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.05018758699952741
+                                                                    "self": 0.1028438780012948
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.004049263000524661,
+                                                                    "total": 0.011734683001122903,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0007459380012733163,
+                                                                    "self": 0.0051198450091760606,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0033033249992513447,
+                                                                            "total": 0.0066148379919468425,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0033033249992513447
+                                                                            "self": 0.0066148379919468425
                                                                         }
                                                                     }
                                                                 }
@@ -315,50 +315,50 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1168.6351722580303,
-                                                    "count": 44652,
+                                                    "total": 891.5829327467582,
+                                                    "count": 34066,
                                                     "is_parallel": true,
-                                                    "self": 65.30438257748574,
+                                                    "self": 48.92964611683783,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 39.80876897196504,
-                                                            "count": 44652,
+                                                            "total": 29.60396611476608,
+                                                            "count": 34066,
                                                             "is_parallel": true,
-                                                            "self": 39.80876897196504
+                                                            "self": 29.60396611476608
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 864.7925276559181,
-                                                            "count": 44652,
+                                                            "total": 661.4653818358129,
+                                                            "count": 34066,
                                                             "is_parallel": true,
-                                                            "self": 864.7925276559181
+                                                            "self": 661.4653818358129
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 198.72949305266138,
-                                                            "count": 89304,
+                                                            "total": 151.58393867934137,
+                                                            "count": 68132,
                                                             "is_parallel": true,
-                                                            "self": 38.26515548550469,
+                                                            "self": 28.717880760199478,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 160.4643375671567,
-                                                                    "count": 357216,
+                                                                    "total": 122.8660579191419,
+                                                                    "count": 272528,
                                                                     "is_parallel": true,
-                                                                    "self": 160.4643375671567
+                                                                    "self": 122.8660579191419
                                                                 }
                                                             }
                                                         }
                                                     }
                                                 },
                                                 "steps_from_proto": {
-                                                    "total": 0.01044114699743659,
-                                                    "count": 6,
+                                                    "total": 0.006653090000327211,
+                                                    "count": 4,
                                                     "is_parallel": true,
-                                                    "self": 0.0021060519966340507,
+                                                    "self": 0.0012782299854734447,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.00833509500080254,
-                                                            "count": 24,
+                                                            "total": 0.005374860014853766,
+                                                            "count": 16,
                                                             "is_parallel": true,
-                                                            "self": 0.00833509500080254
+                                                            "self": 0.005374860014853766
                                                         }
                                                     }
                                                 }
@@ -369,31 +369,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 6768.846438462022,
-                            "count": 44653,
-                            "self": 18.567117787021743,
+                            "total": 1954.408886623518,
+                            "count": 34067,
+                            "self": 13.683372884632263,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 338.1248233489987,
-                                    "count": 44653,
-                                    "self": 337.7347562539999,
+                                    "total": 238.1851148098758,
+                                    "count": 34067,
+                                    "self": 237.6776734658779,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.39006709499881254,
+                                            "total": 0.5074413439979253,
                                             "count": 1,
-                                            "self": 0.39006709499881254
+                                            "self": 0.5074413439979253
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 6412.154497326002,
-                                    "count": 13,
-                                    "self": 194.68812328197782,
+                                    "total": 1702.5403989290098,
+                                    "count": 46,
+                                    "self": 131.7693258140025,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 6217.466374044024,
-                                            "count": 7929,
-                                            "self": 6217.466374044024
+                                            "total": 1570.7710731150073,
+                                            "count": 1446,
+                                            "self": 1570.7710731150073
                                         }
                                     }
                                 }
@@ -402,19 +402,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 2.233000486739911e-06,
+                    "total": 1.8499995348975062e-06,
                     "count": 1,
-                    "self": 2.233000486739911e-06
+                    "self": 1.8499995348975062e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.46970971199880296,
+                    "total": 0.4543389579994255,
                     "count": 1,
-                    "self": 0.00894910799797799,
+                    "self": 0.006759124000382144,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.46076060400082497,
+                            "total": 0.44757983399904333,
                             "count": 1,
-                            "self": 0.46076060400082497
+                            "self": 0.44757983399904333
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,32 +2,32 @@
     "SoccerTwos": {
         "checkpoints": [
             {
-                "steps": 499034,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-499034.onnx",
+                "steps": 499020,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-499020.onnx",
                 "reward": 0.0,
-                "creation_time": 1680453538.97965,
+                "creation_time": 1680466380.7607825,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-499034.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-499020.pt"
                 ]
             },
             {
-                "steps": 682414,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-682414.onnx",
+                "steps": 522784,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-522784.onnx",
                 "reward": 0.0,
-                "creation_time": 1680456446.1206112,
+                "creation_time": 1680466520.5326993,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-682414.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-522784.pt"
                 ]
             }
         ],
-        "elo": 1199.3336962435726,
+        "elo": 1219.1562696291426,
         "final_checkpoint": {
-            "steps": 682414,
+            "steps": 522784,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1680456446.1206112,
+            "creation_time": 1680466520.5326993,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-682414.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-522784.pt"
             ]
         }
     },