First training of PushBlock
Browse files- PushBlock.onnx +1 -1
- PushBlock/{PushBlock-499986.onnx → PushBlock-1499996.onnx} +1 -1
- PushBlock/{PushBlock-499986.pt → PushBlock-1499996.pt} +1 -1
- PushBlock/PushBlock-1999983.onnx +3 -0
- PushBlock/PushBlock-1999983.pt +3 -0
- PushBlock/PushBlock-2000021.onnx +3 -0
- PushBlock/PushBlock-2000021.pt +3 -0
- PushBlock/checkpoint.pt +1 -1
- PushBlock/events.out.tfevents.1673614210.65a2ce5a84bc.21579.0 +3 -0
- config.json +1 -1
- configuration.yaml +3 -3
- run_logs/Player-0.log +13 -13
- run_logs/timers.json +170 -170
- run_logs/training_status.json +31 -13
PushBlock.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 488603
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2022ac008d49c2a5d4238db9a04ae9794a4b8ab4c710d19215f8937e3a841164
|
3 |
size 488603
|
PushBlock/{PushBlock-499986.onnx → PushBlock-1499996.onnx}
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 488603
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75b1328a526eb7fbd0ede19f9ac15d4cc59761efbe54001a07272f1027de9876
|
3 |
size 488603
|
PushBlock/{PushBlock-499986.pt → PushBlock-1499996.pt}
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2915908
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:932b678fdd78809087d775de2020c47d661e98a4ef19c7e523411fd14a2b0550
|
3 |
size 2915908
|
PushBlock/PushBlock-1999983.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2022ac008d49c2a5d4238db9a04ae9794a4b8ab4c710d19215f8937e3a841164
|
3 |
+
size 488603
|
PushBlock/PushBlock-1999983.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e3725f65c1589da655311406d7bf330f6ad226cfd63f6a32675ff3bcc76b67a
|
3 |
+
size 2915908
|
PushBlock/PushBlock-2000021.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2022ac008d49c2a5d4238db9a04ae9794a4b8ab4c710d19215f8937e3a841164
|
3 |
+
size 488603
|
PushBlock/PushBlock-2000021.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a45e4abe5f8d123b3b19650a64758527b7bc0badefaf66503662dcace3eca694
|
3 |
+
size 2915908
|
PushBlock/checkpoint.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2915908
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a45e4abe5f8d123b3b19650a64758527b7bc0badefaf66503662dcace3eca694
|
3 |
size 2915908
|
PushBlock/events.out.tfevents.1673614210.65a2ce5a84bc.21579.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebd98f1fdda90ccbba2041494c8664f8b531b2a453c101787fe7d5447acdfd5f
|
3 |
+
size 167021
|
config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"default_settings": null, "behaviors": {"PushBlock": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 256, "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, "checkpoint_interval": 500000, "max_steps":
|
|
|
1 |
+
{"default_settings": null, "behaviors": {"PushBlock": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 256, "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, "checkpoint_interval": 500000, "max_steps": 2000000, "time_horizon": 64, "summary_freq": 60000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/PushBlock/PushBlock", "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": "PushBlock Training", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
|
configuration.yaml
CHANGED
@@ -36,7 +36,7 @@ behaviors:
|
|
36 |
init_path: null
|
37 |
keep_checkpoints: 5
|
38 |
checkpoint_interval: 500000
|
39 |
-
max_steps:
|
40 |
time_horizon: 64
|
41 |
summary_freq: 60000
|
42 |
threaded: false
|
@@ -65,8 +65,8 @@ checkpoint_settings:
|
|
65 |
run_id: PushBlock Training
|
66 |
initialize_from: null
|
67 |
load_model: false
|
68 |
-
resume:
|
69 |
-
force:
|
70 |
train_model: false
|
71 |
inference: false
|
72 |
results_dir: results
|
|
|
36 |
init_path: null
|
37 |
keep_checkpoints: 5
|
38 |
checkpoint_interval: 500000
|
39 |
+
max_steps: 2000000
|
40 |
time_horizon: 64
|
41 |
summary_freq: 60000
|
42 |
threaded: false
|
|
|
65 |
run_id: PushBlock Training
|
66 |
initialize_from: null
|
67 |
load_model: false
|
68 |
+
resume: true
|
69 |
+
force: false
|
70 |
train_model: false
|
71 |
inference: false
|
72 |
results_dir: results
|
run_logs/Player-0.log
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
Mono path[0] = '/content/ml-agents/training-envs-executables/linux/PushBlock/PushBlock_Data/Managed'
|
2 |
Mono config path = '/content/ml-agents/training-envs-executables/linux/PushBlock/PushBlock_Data/MonoBleedingEdge/etc'
|
3 |
Found 1 interfaces on host : 0) 172.28.0.2
|
4 |
-
Multi-casting "[IP] 172.28.0.2 [Port]
|
5 |
Preloaded 'lib_burst_generated.so'
|
6 |
Preloaded 'libgrpc_csharp_ext.x64.so'
|
7 |
Initialize engine version: 2021.3.5f1 (40eb3a945986)
|
@@ -33,7 +33,7 @@ ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM default
|
|
33 |
FMOD failed to initialize the output device.: "Error initializing output device. " (60)
|
34 |
FMOD initialized on nosound output
|
35 |
Begin MonoManager ReloadAssembly
|
36 |
-
- Completed reload, in 0.
|
37 |
ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
38 |
ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
39 |
ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
@@ -65,7 +65,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
|
|
65 |
WARNING: Shader Unsupported: 'Standard' - All subshaders removed
|
66 |
WARNING: Shader Did you use #pragma only_renderers and omit this platform?
|
67 |
WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
|
68 |
-
UnloadTime: 0.
|
69 |
ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
70 |
requesting resize 84 x 84
|
71 |
Setting up 1 worker threads for Enlighten.
|
@@ -183,12 +183,12 @@ PlayerConnection::CleanupMemory Statistics:
|
|
183 |
Current Block Size 256.0 KB
|
184 |
Peak Allocated Bytes 0.8 KB
|
185 |
Overflow Count 0
|
186 |
-
[ALLOC_TEMP_Background Job.Worker
|
187 |
Initial Block Size 32.0 KB
|
188 |
Current Block Size 32.0 KB
|
189 |
Peak Allocated Bytes 0 B
|
190 |
Overflow Count 0
|
191 |
-
[ALLOC_TEMP_Background Job.Worker
|
192 |
Initial Block Size 32.0 KB
|
193 |
Current Block Size 32.0 KB
|
194 |
Peak Allocated Bytes 0 B
|
@@ -210,7 +210,7 @@ PlayerConnection::CleanupMemory Statistics:
|
|
210 |
Peak Allocated memory 152.1 KB
|
211 |
Peak Large allocation bytes 0 B
|
212 |
[ALLOC_DEFAULT] Dual Thread Allocator
|
213 |
-
Peak main deferred allocation count
|
214 |
[ALLOC_BUCKET]
|
215 |
Large Block size 4.0 MB
|
216 |
Used Block count 1
|
@@ -219,13 +219,13 @@ PlayerConnection::CleanupMemory Statistics:
|
|
219 |
Peak usage frame count: [4.0 MB-8.0 MB]: 9381 frames
|
220 |
Requested Block Size 16.0 MB
|
221 |
Peak Block count 1
|
222 |
-
Peak Allocated memory 5.
|
223 |
Peak Large allocation bytes 0 B
|
224 |
[ALLOC_DEFAULT_THREAD]
|
225 |
Peak usage frame count: [16.0 MB-32.0 MB]: 9381 frames
|
226 |
Requested Block Size 16.0 MB
|
227 |
Peak Block count 1
|
228 |
-
Peak Allocated memory 17.
|
229 |
Peak Large allocation bytes 16.0 MB
|
230 |
[ALLOC_TEMP_JOB_1_FRAME]
|
231 |
Initial Block Size 2.0 MB
|
@@ -278,10 +278,10 @@ PlayerConnection::CleanupMemory Statistics:
|
|
278 |
Peak Allocated memory 0.6 MB
|
279 |
Peak Large allocation bytes 0 B
|
280 |
[ALLOC_CACHEOBJECTS_THREAD]
|
281 |
-
Peak usage frame count: [0.5 MB-1.0 MB]: 9380 frames, [
|
282 |
Requested Block Size 4.0 MB
|
283 |
-
Peak Block count
|
284 |
-
Peak Allocated memory 3
|
285 |
Peak Large allocation bytes 0 B
|
286 |
[ALLOC_TYPETREE] Dual Thread Allocator
|
287 |
Peak main deferred allocation count 0
|
@@ -305,10 +305,10 @@ PlayerConnection::CleanupMemory Statistics:
|
|
305 |
Peak usage frame count: [16.0 KB-32.0 KB]: 9381 frames
|
306 |
Requested Block Size 16.0 MB
|
307 |
Peak Block count 1
|
308 |
-
Peak Allocated memory
|
309 |
Peak Large allocation bytes 0 B
|
310 |
[ALLOC_PROFILER_BUCKET]
|
311 |
Large Block size 4.0 MB
|
312 |
Used Block count 1
|
313 |
Peak Allocated bytes 332 B
|
314 |
-
##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":
|
|
|
1 |
Mono path[0] = '/content/ml-agents/training-envs-executables/linux/PushBlock/PushBlock_Data/Managed'
|
2 |
Mono config path = '/content/ml-agents/training-envs-executables/linux/PushBlock/PushBlock_Data/MonoBleedingEdge/etc'
|
3 |
Found 1 interfaces on host : 0) 172.28.0.2
|
4 |
+
Multi-casting "[IP] 172.28.0.2 [Port] 55196 [Flags] 2 [Guid] 3627192237 [EditorId] 588871222 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
|
5 |
Preloaded 'lib_burst_generated.so'
|
6 |
Preloaded 'libgrpc_csharp_ext.x64.so'
|
7 |
Initialize engine version: 2021.3.5f1 (40eb3a945986)
|
|
|
33 |
FMOD failed to initialize the output device.: "Error initializing output device. " (60)
|
34 |
FMOD initialized on nosound output
|
35 |
Begin MonoManager ReloadAssembly
|
36 |
+
- Completed reload, in 0.080 seconds
|
37 |
ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
38 |
ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
39 |
ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
|
|
65 |
WARNING: Shader Unsupported: 'Standard' - All subshaders removed
|
66 |
WARNING: Shader Did you use #pragma only_renderers and omit this platform?
|
67 |
WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
|
68 |
+
UnloadTime: 0.783054 ms
|
69 |
ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
70 |
requesting resize 84 x 84
|
71 |
Setting up 1 worker threads for Enlighten.
|
|
|
183 |
Current Block Size 256.0 KB
|
184 |
Peak Allocated Bytes 0.8 KB
|
185 |
Overflow Count 0
|
186 |
+
[ALLOC_TEMP_Background Job.Worker 14]
|
187 |
Initial Block Size 32.0 KB
|
188 |
Current Block Size 32.0 KB
|
189 |
Peak Allocated Bytes 0 B
|
190 |
Overflow Count 0
|
191 |
+
[ALLOC_TEMP_Background Job.Worker 9]
|
192 |
Initial Block Size 32.0 KB
|
193 |
Current Block Size 32.0 KB
|
194 |
Peak Allocated Bytes 0 B
|
|
|
210 |
Peak Allocated memory 152.1 KB
|
211 |
Peak Large allocation bytes 0 B
|
212 |
[ALLOC_DEFAULT] Dual Thread Allocator
|
213 |
+
Peak main deferred allocation count 10
|
214 |
[ALLOC_BUCKET]
|
215 |
Large Block size 4.0 MB
|
216 |
Used Block count 1
|
|
|
219 |
Peak usage frame count: [4.0 MB-8.0 MB]: 9381 frames
|
220 |
Requested Block Size 16.0 MB
|
221 |
Peak Block count 1
|
222 |
+
Peak Allocated memory 5.5 MB
|
223 |
Peak Large allocation bytes 0 B
|
224 |
[ALLOC_DEFAULT_THREAD]
|
225 |
Peak usage frame count: [16.0 MB-32.0 MB]: 9381 frames
|
226 |
Requested Block Size 16.0 MB
|
227 |
Peak Block count 1
|
228 |
+
Peak Allocated memory 17.1 MB
|
229 |
Peak Large allocation bytes 16.0 MB
|
230 |
[ALLOC_TEMP_JOB_1_FRAME]
|
231 |
Initial Block Size 2.0 MB
|
|
|
278 |
Peak Allocated memory 0.6 MB
|
279 |
Peak Large allocation bytes 0 B
|
280 |
[ALLOC_CACHEOBJECTS_THREAD]
|
281 |
+
Peak usage frame count: [0.5 MB-1.0 MB]: 9380 frames, [4.0 MB-8.0 MB]: 1 frames
|
282 |
Requested Block Size 4.0 MB
|
283 |
+
Peak Block count 2
|
284 |
+
Peak Allocated memory 4.3 MB
|
285 |
Peak Large allocation bytes 0 B
|
286 |
[ALLOC_TYPETREE] Dual Thread Allocator
|
287 |
Peak main deferred allocation count 0
|
|
|
305 |
Peak usage frame count: [16.0 KB-32.0 KB]: 9381 frames
|
306 |
Requested Block Size 16.0 MB
|
307 |
Peak Block count 1
|
308 |
+
Peak Allocated memory 27.9 KB
|
309 |
Peak Large allocation bytes 0 B
|
310 |
[ALLOC_PROFILER_BUCKET]
|
311 |
Large Block size 4.0 MB
|
312 |
Used Block count 1
|
313 |
Peak Allocated bytes 332 B
|
314 |
+
##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1673615253482,"processId":21596,"allocatedMemory":1957338,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3453},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}
|
run_logs/timers.json
CHANGED
@@ -2,220 +2,220 @@
|
|
2 |
"name": "root",
|
3 |
"gauges": {
|
4 |
"PushBlock.Policy.Entropy.mean": {
|
5 |
-
"value": 0.
|
6 |
-
"min": 0.
|
7 |
-
"max":
|
8 |
-
"count":
|
9 |
},
|
10 |
"PushBlock.Policy.Entropy.sum": {
|
11 |
-
"value":
|
12 |
-
"min":
|
13 |
-
"max":
|
14 |
-
"count":
|
15 |
},
|
16 |
"PushBlock.Environment.EpisodeLength.mean": {
|
17 |
-
"value":
|
18 |
-
"min":
|
19 |
-
"max":
|
20 |
-
"count":
|
21 |
},
|
22 |
"PushBlock.Environment.EpisodeLength.sum": {
|
23 |
-
"value":
|
24 |
-
"min":
|
25 |
-
"max":
|
26 |
-
"count":
|
27 |
},
|
28 |
"PushBlock.Step.mean": {
|
29 |
-
"value":
|
30 |
-
"min":
|
31 |
-
"max":
|
32 |
-
"count":
|
33 |
},
|
34 |
"PushBlock.Step.sum": {
|
35 |
-
"value":
|
36 |
-
"min":
|
37 |
-
"max":
|
38 |
-
"count":
|
39 |
},
|
40 |
"PushBlock.Policy.ExtrinsicValueEstimate.mean": {
|
41 |
-
"value":
|
42 |
-
"min":
|
43 |
-
"max": 4.
|
44 |
-
"count":
|
45 |
},
|
46 |
"PushBlock.Policy.ExtrinsicValueEstimate.sum": {
|
47 |
-
"value":
|
48 |
-
"min":
|
49 |
-
"max":
|
50 |
-
"count":
|
51 |
},
|
52 |
"PushBlock.Environment.CumulativeReward.mean": {
|
53 |
-
"value": 4.
|
54 |
-
"min":
|
55 |
-
"max": 4.
|
56 |
-
"count":
|
57 |
},
|
58 |
"PushBlock.Environment.CumulativeReward.sum": {
|
59 |
-
"value":
|
60 |
-
"min":
|
61 |
-
"max":
|
62 |
-
"count":
|
63 |
},
|
64 |
"PushBlock.Policy.ExtrinsicReward.mean": {
|
65 |
-
"value": 4.
|
66 |
-
"min":
|
67 |
-
"max": 4.
|
68 |
-
"count":
|
69 |
},
|
70 |
"PushBlock.Policy.ExtrinsicReward.sum": {
|
71 |
-
"value":
|
72 |
-
"min":
|
73 |
-
"max":
|
74 |
-
"count":
|
75 |
},
|
76 |
"PushBlock.Losses.PolicyLoss.mean": {
|
77 |
-
"value": 0.
|
78 |
-
"min": 0.
|
79 |
-
"max": 0.
|
80 |
-
"count":
|
81 |
},
|
82 |
"PushBlock.Losses.PolicyLoss.sum": {
|
83 |
-
"value": 1.
|
84 |
-
"min":
|
85 |
-
"max": 2.
|
86 |
-
"count":
|
87 |
},
|
88 |
"PushBlock.Losses.ValueLoss.mean": {
|
89 |
-
"value": 0.
|
90 |
-
"min": 0.
|
91 |
-
"max": 0.
|
92 |
-
"count":
|
93 |
},
|
94 |
"PushBlock.Losses.ValueLoss.sum": {
|
95 |
-
"value":
|
96 |
-
"min":
|
97 |
-
"max":
|
98 |
-
"count":
|
99 |
},
|
100 |
"PushBlock.Policy.LearningRate.mean": {
|
101 |
-
"value":
|
102 |
-
"min":
|
103 |
-
"max": 0.
|
104 |
-
"count":
|
105 |
},
|
106 |
"PushBlock.Policy.LearningRate.sum": {
|
107 |
-
"value": 0.
|
108 |
-
"min": 0.
|
109 |
-
"max": 0.
|
110 |
-
"count":
|
111 |
},
|
112 |
"PushBlock.Policy.Epsilon.mean": {
|
113 |
-
"value": 0.
|
114 |
-
"min": 0.
|
115 |
-
"max": 0.
|
116 |
-
"count":
|
117 |
},
|
118 |
"PushBlock.Policy.Epsilon.sum": {
|
119 |
-
"value":
|
120 |
-
"min":
|
121 |
-
"max":
|
122 |
-
"count":
|
123 |
},
|
124 |
"PushBlock.Policy.Beta.mean": {
|
125 |
-
"value": 0.
|
126 |
-
"min": 0.
|
127 |
-
"max": 0.
|
128 |
-
"count":
|
129 |
},
|
130 |
"PushBlock.Policy.Beta.sum": {
|
131 |
-
"value": 0.
|
132 |
-
"min": 0.
|
133 |
-
"max": 0.
|
134 |
-
"count":
|
135 |
},
|
136 |
"PushBlock.IsTraining.mean": {
|
137 |
"value": 1.0,
|
138 |
"min": 1.0,
|
139 |
"max": 1.0,
|
140 |
-
"count":
|
141 |
},
|
142 |
"PushBlock.IsTraining.sum": {
|
143 |
"value": 1.0,
|
144 |
"min": 1.0,
|
145 |
"max": 1.0,
|
146 |
-
"count":
|
147 |
}
|
148 |
},
|
149 |
"metadata": {
|
150 |
"timer_format_version": "0.1.0",
|
151 |
-
"start_time_seconds": "
|
152 |
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
|
153 |
-
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PushBlock.yaml --env=./training-envs-executables/linux/PushBlock/PushBlock --run-id=PushBlock Training --no-graphics --
|
154 |
"mlagents_version": "0.29.0.dev0",
|
155 |
"mlagents_envs_version": "0.29.0.dev0",
|
156 |
"communication_protocol_version": "1.5.0",
|
157 |
"pytorch_version": "1.8.1+cu102",
|
158 |
"numpy_version": "1.21.6",
|
159 |
-
"end_time_seconds": "
|
160 |
},
|
161 |
-
"total":
|
162 |
"count": 1,
|
163 |
-
"self": 0.
|
164 |
"children": {
|
165 |
"run_training.setup": {
|
166 |
-
"total": 0.
|
167 |
"count": 1,
|
168 |
-
"self": 0.
|
169 |
},
|
170 |
"TrainerController.start_learning": {
|
171 |
-
"total":
|
172 |
"count": 1,
|
173 |
-
"self":
|
174 |
"children": {
|
175 |
"TrainerController._reset_env": {
|
176 |
-
"total": 6.
|
177 |
"count": 1,
|
178 |
-
"self": 6.
|
179 |
},
|
180 |
"TrainerController.advance": {
|
181 |
-
"total":
|
182 |
-
"count":
|
183 |
-
"self":
|
184 |
"children": {
|
185 |
"env_step": {
|
186 |
-
"total":
|
187 |
-
"count":
|
188 |
-
"self":
|
189 |
"children": {
|
190 |
"SubprocessEnvManager._take_step": {
|
191 |
-
"total":
|
192 |
-
"count":
|
193 |
-
"self": 2.
|
194 |
"children": {
|
195 |
"TorchPolicy.evaluate": {
|
196 |
-
"total":
|
197 |
-
"count":
|
198 |
-
"self": 15.
|
199 |
"children": {
|
200 |
"TorchPolicy.sample_actions": {
|
201 |
-
"total":
|
202 |
-
"count":
|
203 |
-
"self":
|
204 |
}
|
205 |
}
|
206 |
}
|
207 |
}
|
208 |
},
|
209 |
"workers": {
|
210 |
-
"total": 0.
|
211 |
-
"count":
|
212 |
"self": 0.0,
|
213 |
"children": {
|
214 |
"worker_root": {
|
215 |
-
"total":
|
216 |
-
"count":
|
217 |
"is_parallel": true,
|
218 |
-
"self":
|
219 |
"children": {
|
220 |
"run_training.setup": {
|
221 |
"total": 0.0,
|
@@ -224,48 +224,48 @@
|
|
224 |
"self": 0.0,
|
225 |
"children": {
|
226 |
"steps_from_proto": {
|
227 |
-
"total": 0.
|
228 |
"count": 1,
|
229 |
"is_parallel": true,
|
230 |
-
"self": 0.
|
231 |
"children": {
|
232 |
"_process_rank_one_or_two_observation": {
|
233 |
-
"total": 0.
|
234 |
"count": 4,
|
235 |
"is_parallel": true,
|
236 |
-
"self": 0.
|
237 |
}
|
238 |
}
|
239 |
},
|
240 |
"UnityEnvironment.step": {
|
241 |
-
"total": 0.
|
242 |
"count": 1,
|
243 |
"is_parallel": true,
|
244 |
-
"self": 0.
|
245 |
"children": {
|
246 |
"UnityEnvironment._generate_step_input": {
|
247 |
-
"total": 0.
|
248 |
"count": 1,
|
249 |
"is_parallel": true,
|
250 |
-
"self": 0.
|
251 |
},
|
252 |
"communicator.exchange": {
|
253 |
-
"total": 0.
|
254 |
"count": 1,
|
255 |
"is_parallel": true,
|
256 |
-
"self": 0.
|
257 |
},
|
258 |
"steps_from_proto": {
|
259 |
-
"total": 0.
|
260 |
"count": 1,
|
261 |
"is_parallel": true,
|
262 |
-
"self": 0.
|
263 |
"children": {
|
264 |
"_process_rank_one_or_two_observation": {
|
265 |
-
"total": 0.
|
266 |
"count": 4,
|
267 |
"is_parallel": true,
|
268 |
-
"self": 0.
|
269 |
}
|
270 |
}
|
271 |
}
|
@@ -274,34 +274,34 @@
|
|
274 |
}
|
275 |
},
|
276 |
"UnityEnvironment.step": {
|
277 |
-
"total":
|
278 |
-
"count":
|
279 |
"is_parallel": true,
|
280 |
-
"self":
|
281 |
"children": {
|
282 |
"UnityEnvironment._generate_step_input": {
|
283 |
-
"total": 20.
|
284 |
-
"count":
|
285 |
"is_parallel": true,
|
286 |
-
"self": 20.
|
287 |
},
|
288 |
"communicator.exchange": {
|
289 |
-
"total":
|
290 |
-
"count":
|
291 |
"is_parallel": true,
|
292 |
-
"self":
|
293 |
},
|
294 |
"steps_from_proto": {
|
295 |
-
"total":
|
296 |
-
"count":
|
297 |
"is_parallel": true,
|
298 |
-
"self":
|
299 |
"children": {
|
300 |
"_process_rank_one_or_two_observation": {
|
301 |
-
"total":
|
302 |
-
"count":
|
303 |
"is_parallel": true,
|
304 |
-
"self":
|
305 |
}
|
306 |
}
|
307 |
}
|
@@ -314,31 +314,31 @@
|
|
314 |
}
|
315 |
},
|
316 |
"trainer_advance": {
|
317 |
-
"total":
|
318 |
-
"count":
|
319 |
-
"self": 1.
|
320 |
"children": {
|
321 |
"process_trajectory": {
|
322 |
-
"total":
|
323 |
-
"count":
|
324 |
-
"self":
|
325 |
"children": {
|
326 |
"RLTrainer._checkpoint": {
|
327 |
-
"total": 0.
|
328 |
"count": 2,
|
329 |
-
"self": 0.
|
330 |
}
|
331 |
}
|
332 |
},
|
333 |
"_update_policy": {
|
334 |
-
"total":
|
335 |
-
"count":
|
336 |
-
"self":
|
337 |
"children": {
|
338 |
"TorchPPOOptimizer.update": {
|
339 |
-
"total":
|
340 |
-
"count":
|
341 |
-
"self":
|
342 |
}
|
343 |
}
|
344 |
}
|
@@ -347,19 +347,19 @@
|
|
347 |
}
|
348 |
},
|
349 |
"trainer_threads": {
|
350 |
-
"total":
|
351 |
"count": 1,
|
352 |
-
"self":
|
353 |
},
|
354 |
"TrainerController._save_models": {
|
355 |
-
"total": 0.
|
356 |
"count": 1,
|
357 |
-
"self": 0.
|
358 |
"children": {
|
359 |
"RLTrainer._checkpoint": {
|
360 |
-
"total": 0.
|
361 |
"count": 1,
|
362 |
-
"self": 0.
|
363 |
}
|
364 |
}
|
365 |
}
|
|
|
2 |
"name": "root",
|
3 |
"gauges": {
|
4 |
"PushBlock.Policy.Entropy.mean": {
|
5 |
+
"value": 0.3053772449493408,
|
6 |
+
"min": 0.3053772449493408,
|
7 |
+
"max": 0.5504772067070007,
|
8 |
+
"count": 17
|
9 |
},
|
10 |
"PushBlock.Policy.Entropy.sum": {
|
11 |
+
"value": 18322.634765625,
|
12 |
+
"min": 9597.37109375,
|
13 |
+
"max": 33116.70703125,
|
14 |
+
"count": 17
|
15 |
},
|
16 |
"PushBlock.Environment.EpisodeLength.mean": {
|
17 |
+
"value": 24.497107438016528,
|
18 |
+
"min": 20.855681818181818,
|
19 |
+
"max": 31.356839872746555,
|
20 |
+
"count": 17
|
21 |
},
|
22 |
"PushBlock.Environment.EpisodeLength.sum": {
|
23 |
+
"value": 59283.0,
|
24 |
+
"min": 18353.0,
|
25 |
+
"max": 62565.0,
|
26 |
+
"count": 17
|
27 |
},
|
28 |
"PushBlock.Step.mean": {
|
29 |
+
"value": 1979978.0,
|
30 |
+
"min": 1019994.0,
|
31 |
+
"max": 1979978.0,
|
32 |
+
"count": 17
|
33 |
},
|
34 |
"PushBlock.Step.sum": {
|
35 |
+
"value": 1979978.0,
|
36 |
+
"min": 1019994.0,
|
37 |
+
"max": 1979978.0,
|
38 |
+
"count": 17
|
39 |
},
|
40 |
"PushBlock.Policy.ExtrinsicValueEstimate.mean": {
|
41 |
+
"value": 4.202976703643799,
|
42 |
+
"min": 3.9554073810577393,
|
43 |
+
"max": 4.381915092468262,
|
44 |
+
"count": 17
|
45 |
},
|
46 |
"PushBlock.Policy.ExtrinsicValueEstimate.sum": {
|
47 |
+
"value": 11121.076171875,
|
48 |
+
"min": 4022.59814453125,
|
49 |
+
"max": 11121.076171875,
|
50 |
+
"count": 17
|
51 |
},
|
52 |
"PushBlock.Environment.CumulativeReward.mean": {
|
53 |
+
"value": 4.948017998720998,
|
54 |
+
"min": 4.91599571979678,
|
55 |
+
"max": 4.978548857768038,
|
56 |
+
"count": 17
|
57 |
},
|
58 |
"PushBlock.Environment.CumulativeReward.sum": {
|
59 |
+
"value": 11964.307520907372,
|
60 |
+
"min": 4376.144445978105,
|
61 |
+
"max": 11964.307520907372,
|
62 |
+
"count": 17
|
63 |
},
|
64 |
"PushBlock.Policy.ExtrinsicReward.mean": {
|
65 |
+
"value": 4.948017998720998,
|
66 |
+
"min": 4.91599571979678,
|
67 |
+
"max": 4.978548857768038,
|
68 |
+
"count": 17
|
69 |
},
|
70 |
"PushBlock.Policy.ExtrinsicReward.sum": {
|
71 |
+
"value": 11964.307520907372,
|
72 |
+
"min": 4376.144445978105,
|
73 |
+
"max": 11964.307520907372,
|
74 |
+
"count": 17
|
75 |
},
|
76 |
"PushBlock.Losses.PolicyLoss.mean": {
|
77 |
+
"value": 0.06854083736316066,
|
78 |
+
"min": 0.06570367596745116,
|
79 |
+
"max": 0.07293808065895419,
|
80 |
+
"count": 17
|
81 |
},
|
82 |
"PushBlock.Losses.PolicyLoss.sum": {
|
83 |
+
"value": 1.987684283531659,
|
84 |
+
"min": 0.6080501811423649,
|
85 |
+
"max": 2.1152043391096713,
|
86 |
+
"count": 17
|
87 |
},
|
88 |
"PushBlock.Losses.ValueLoss.mean": {
|
89 |
+
"value": 0.16020560359860633,
|
90 |
+
"min": 0.11079794753135908,
|
91 |
+
"max": 0.20724302395942737,
|
92 |
+
"count": 17
|
93 |
},
|
94 |
"PushBlock.Losses.ValueLoss.sum": {
|
95 |
+
"value": 4.645962504359583,
|
96 |
+
"min": 0.9971815277822317,
|
97 |
+
"max": 6.010047694823394,
|
98 |
+
"count": 17
|
99 |
},
|
100 |
"PushBlock.Policy.LearningRate.mean": {
|
101 |
+
"value": 7.470573371910346e-06,
|
102 |
+
"min": 7.470573371910346e-06,
|
103 |
+
"max": 0.0001484476671841278,
|
104 |
+
"count": 17
|
105 |
},
|
106 |
"PushBlock.Policy.LearningRate.sum": {
|
107 |
+
"value": 0.00021664662778540005,
|
108 |
+
"min": 0.00021664662778540005,
|
109 |
+
"max": 0.00413402807199115,
|
110 |
+
"count": 17
|
111 |
},
|
112 |
"PushBlock.Policy.Epsilon.mean": {
|
113 |
+
"value": 0.10249015862068965,
|
114 |
+
"min": 0.10249015862068965,
|
115 |
+
"max": 0.14948253888888888,
|
116 |
+
"count": 17
|
117 |
},
|
118 |
"PushBlock.Policy.Epsilon.sum": {
|
119 |
+
"value": 2.9722146,
|
120 |
+
"min": 1.34534285,
|
121 |
+
"max": 4.278008850000001,
|
122 |
+
"count": 17
|
123 |
},
|
124 |
"PushBlock.Policy.Beta.mean": {
|
125 |
+
"value": 0.00025876684620689666,
|
126 |
+
"min": 0.00025876684620689666,
|
127 |
+
"max": 0.0049533056349999995,
|
128 |
+
"count": 17
|
129 |
},
|
130 |
"PushBlock.Policy.Beta.sum": {
|
131 |
+
"value": 0.007504238540000004,
|
132 |
+
"min": 0.007504238540000004,
|
133 |
+
"max": 0.137953084115,
|
134 |
+
"count": 17
|
135 |
},
|
136 |
"PushBlock.IsTraining.mean": {
|
137 |
"value": 1.0,
|
138 |
"min": 1.0,
|
139 |
"max": 1.0,
|
140 |
+
"count": 17
|
141 |
},
|
142 |
"PushBlock.IsTraining.sum": {
|
143 |
"value": 1.0,
|
144 |
"min": 1.0,
|
145 |
"max": 1.0,
|
146 |
+
"count": 17
|
147 |
}
|
148 |
},
|
149 |
"metadata": {
|
150 |
"timer_format_version": "0.1.0",
|
151 |
+
"start_time_seconds": "1673614207",
|
152 |
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
|
153 |
+
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PushBlock.yaml --env=./training-envs-executables/linux/PushBlock/PushBlock --run-id=PushBlock Training --no-graphics --resume",
|
154 |
"mlagents_version": "0.29.0.dev0",
|
155 |
"mlagents_envs_version": "0.29.0.dev0",
|
156 |
"communication_protocol_version": "1.5.0",
|
157 |
"pytorch_version": "1.8.1+cu102",
|
158 |
"numpy_version": "1.21.6",
|
159 |
+
"end_time_seconds": "1673615253"
|
160 |
},
|
161 |
+
"total": 1046.2137101449998,
|
162 |
"count": 1,
|
163 |
+
"self": 0.3899714359995414,
|
164 |
"children": {
|
165 |
"run_training.setup": {
|
166 |
+
"total": 0.1067486749998352,
|
167 |
"count": 1,
|
168 |
+
"self": 0.1067486749998352
|
169 |
},
|
170 |
"TrainerController.start_learning": {
|
171 |
+
"total": 1045.7169900340004,
|
172 |
"count": 1,
|
173 |
+
"self": 1.1543514471568415,
|
174 |
"children": {
|
175 |
"TrainerController._reset_env": {
|
176 |
+
"total": 6.114223151999795,
|
177 |
"count": 1,
|
178 |
+
"self": 6.114223151999795
|
179 |
},
|
180 |
"TrainerController.advance": {
|
181 |
+
"total": 1038.3885253858443,
|
182 |
+
"count": 56641,
|
183 |
+
"self": 1.082656069944278,
|
184 |
"children": {
|
185 |
"env_step": {
|
186 |
+
"total": 633.3635000969516,
|
187 |
+
"count": 56641,
|
188 |
+
"self": 583.3682616877186,
|
189 |
"children": {
|
190 |
"SubprocessEnvManager._take_step": {
|
191 |
+
"total": 49.34512990503845,
|
192 |
+
"count": 56641,
|
193 |
+
"self": 2.552449484021963,
|
194 |
"children": {
|
195 |
"TorchPolicy.evaluate": {
|
196 |
+
"total": 46.792680421016485,
|
197 |
+
"count": 31268,
|
198 |
+
"self": 15.05989050507742,
|
199 |
"children": {
|
200 |
"TorchPolicy.sample_actions": {
|
201 |
+
"total": 31.732789915939065,
|
202 |
+
"count": 31268,
|
203 |
+
"self": 31.732789915939065
|
204 |
}
|
205 |
}
|
206 |
}
|
207 |
}
|
208 |
},
|
209 |
"workers": {
|
210 |
+
"total": 0.6501085041945771,
|
211 |
+
"count": 56641,
|
212 |
"self": 0.0,
|
213 |
"children": {
|
214 |
"worker_root": {
|
215 |
+
"total": 1042.8514952079759,
|
216 |
+
"count": 56641,
|
217 |
"is_parallel": true,
|
218 |
+
"self": 537.829317073064,
|
219 |
"children": {
|
220 |
"run_training.setup": {
|
221 |
"total": 0.0,
|
|
|
224 |
"self": 0.0,
|
225 |
"children": {
|
226 |
"steps_from_proto": {
|
227 |
+
"total": 0.0021317410000847303,
|
228 |
"count": 1,
|
229 |
"is_parallel": true,
|
230 |
+
"self": 0.0006226960013009375,
|
231 |
"children": {
|
232 |
"_process_rank_one_or_two_observation": {
|
233 |
+
"total": 0.0015090449987837928,
|
234 |
"count": 4,
|
235 |
"is_parallel": true,
|
236 |
+
"self": 0.0015090449987837928
|
237 |
}
|
238 |
}
|
239 |
},
|
240 |
"UnityEnvironment.step": {
|
241 |
+
"total": 0.03177298199989309,
|
242 |
"count": 1,
|
243 |
"is_parallel": true,
|
244 |
+
"self": 0.0007234929980768356,
|
245 |
"children": {
|
246 |
"UnityEnvironment._generate_step_input": {
|
247 |
+
"total": 0.00072096900021279,
|
248 |
"count": 1,
|
249 |
"is_parallel": true,
|
250 |
+
"self": 0.00072096900021279
|
251 |
},
|
252 |
"communicator.exchange": {
|
253 |
+
"total": 0.028191806000904762,
|
254 |
"count": 1,
|
255 |
"is_parallel": true,
|
256 |
+
"self": 0.028191806000904762
|
257 |
},
|
258 |
"steps_from_proto": {
|
259 |
+
"total": 0.002136714000698703,
|
260 |
"count": 1,
|
261 |
"is_parallel": true,
|
262 |
+
"self": 0.0004282770005374914,
|
263 |
"children": {
|
264 |
"_process_rank_one_or_two_observation": {
|
265 |
+
"total": 0.0017084370001612115,
|
266 |
"count": 4,
|
267 |
"is_parallel": true,
|
268 |
+
"self": 0.0017084370001612115
|
269 |
}
|
270 |
}
|
271 |
}
|
|
|
274 |
}
|
275 |
},
|
276 |
"UnityEnvironment.step": {
|
277 |
+
"total": 505.0221781349119,
|
278 |
+
"count": 56640,
|
279 |
"is_parallel": true,
|
280 |
+
"self": 24.26384900564608,
|
281 |
"children": {
|
282 |
"UnityEnvironment._generate_step_input": {
|
283 |
+
"total": 20.097179551136833,
|
284 |
+
"count": 56640,
|
285 |
"is_parallel": true,
|
286 |
+
"self": 20.097179551136833
|
287 |
},
|
288 |
"communicator.exchange": {
|
289 |
+
"total": 384.2496825019816,
|
290 |
+
"count": 56640,
|
291 |
"is_parallel": true,
|
292 |
+
"self": 384.2496825019816
|
293 |
},
|
294 |
"steps_from_proto": {
|
295 |
+
"total": 76.41146707614735,
|
296 |
+
"count": 56640,
|
297 |
"is_parallel": true,
|
298 |
+
"self": 15.360666518023208,
|
299 |
"children": {
|
300 |
"_process_rank_one_or_two_observation": {
|
301 |
+
"total": 61.05080055812414,
|
302 |
+
"count": 226560,
|
303 |
"is_parallel": true,
|
304 |
+
"self": 61.05080055812414
|
305 |
}
|
306 |
}
|
307 |
}
|
|
|
314 |
}
|
315 |
},
|
316 |
"trainer_advance": {
|
317 |
+
"total": 403.94236921894844,
|
318 |
+
"count": 56641,
|
319 |
+
"self": 1.949787357903915,
|
320 |
"children": {
|
321 |
"process_trajectory": {
|
322 |
+
"total": 124.50655854404704,
|
323 |
+
"count": 56641,
|
324 |
+
"self": 124.37395476104757,
|
325 |
"children": {
|
326 |
"RLTrainer._checkpoint": {
|
327 |
+
"total": 0.1326037829994675,
|
328 |
"count": 2,
|
329 |
+
"self": 0.1326037829994675
|
330 |
}
|
331 |
}
|
332 |
},
|
333 |
"_update_policy": {
|
334 |
+
"total": 277.4860233169975,
|
335 |
+
"count": 483,
|
336 |
+
"self": 141.4308676799692,
|
337 |
"children": {
|
338 |
"TorchPPOOptimizer.update": {
|
339 |
+
"total": 136.0551556370283,
|
340 |
+
"count": 23190,
|
341 |
+
"self": 136.0551556370283
|
342 |
}
|
343 |
}
|
344 |
}
|
|
|
347 |
}
|
348 |
},
|
349 |
"trainer_threads": {
|
350 |
+
"total": 8.179995347745717e-07,
|
351 |
"count": 1,
|
352 |
+
"self": 8.179995347745717e-07
|
353 |
},
|
354 |
"TrainerController._save_models": {
|
355 |
+
"total": 0.05988923099994281,
|
356 |
"count": 1,
|
357 |
+
"self": 0.0009487080005783355,
|
358 |
"children": {
|
359 |
"RLTrainer._checkpoint": {
|
360 |
+
"total": 0.058940522999364475,
|
361 |
"count": 1,
|
362 |
+
"self": 0.058940522999364475
|
363 |
}
|
364 |
}
|
365 |
}
|
run_logs/training_status.json
CHANGED
@@ -1,15 +1,6 @@
|
|
1 |
{
|
2 |
"PushBlock": {
|
3 |
"checkpoints": [
|
4 |
-
{
|
5 |
-
"steps": 499986,
|
6 |
-
"file_path": "results/PushBlock Training/PushBlock/PushBlock-499986.onnx",
|
7 |
-
"reward": 4.975390584873302,
|
8 |
-
"creation_time": 1673610359.6582482,
|
9 |
-
"auxillary_file_paths": [
|
10 |
-
"results/PushBlock Training/PushBlock/PushBlock-499986.pt"
|
11 |
-
]
|
12 |
-
},
|
13 |
{
|
14 |
"steps": 999988,
|
15 |
"file_path": "results/PushBlock Training/PushBlock/PushBlock-999988.onnx",
|
@@ -27,15 +18,42 @@
|
|
27 |
"auxillary_file_paths": [
|
28 |
"results/PushBlock Training/PushBlock/PushBlock-1000008.pt"
|
29 |
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
}
|
31 |
],
|
32 |
"final_checkpoint": {
|
33 |
-
"steps":
|
34 |
"file_path": "results/PushBlock Training/PushBlock.onnx",
|
35 |
-
"reward": 4.
|
36 |
-
"creation_time":
|
37 |
"auxillary_file_paths": [
|
38 |
-
"results/PushBlock Training/PushBlock/PushBlock-
|
39 |
]
|
40 |
}
|
41 |
},
|
|
|
1 |
{
|
2 |
"PushBlock": {
|
3 |
"checkpoints": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
{
|
5 |
"steps": 999988,
|
6 |
"file_path": "results/PushBlock Training/PushBlock/PushBlock-999988.onnx",
|
|
|
18 |
"auxillary_file_paths": [
|
19 |
"results/PushBlock Training/PushBlock/PushBlock-1000008.pt"
|
20 |
]
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"steps": 1499996,
|
24 |
+
"file_path": "results/PushBlock Training/PushBlock/PushBlock-1499996.onnx",
|
25 |
+
"reward": 4.981184247489038,
|
26 |
+
"creation_time": 1673614737.4062574,
|
27 |
+
"auxillary_file_paths": [
|
28 |
+
"results/PushBlock Training/PushBlock/PushBlock-1499996.pt"
|
29 |
+
]
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"steps": 1999983,
|
33 |
+
"file_path": "results/PushBlock Training/PushBlock/PushBlock-1999983.onnx",
|
34 |
+
"reward": 4.986760091781616,
|
35 |
+
"creation_time": 1673615253.0382304,
|
36 |
+
"auxillary_file_paths": [
|
37 |
+
"results/PushBlock Training/PushBlock/PushBlock-1999983.pt"
|
38 |
+
]
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"steps": 2000021,
|
42 |
+
"file_path": "results/PushBlock Training/PushBlock/PushBlock-2000021.onnx",
|
43 |
+
"reward": 4.986907775585468,
|
44 |
+
"creation_time": 1673615253.1351264,
|
45 |
+
"auxillary_file_paths": [
|
46 |
+
"results/PushBlock Training/PushBlock/PushBlock-2000021.pt"
|
47 |
+
]
|
48 |
}
|
49 |
],
|
50 |
"final_checkpoint": {
|
51 |
+
"steps": 2000021,
|
52 |
"file_path": "results/PushBlock Training/PushBlock.onnx",
|
53 |
+
"reward": 4.986907775585468,
|
54 |
+
"creation_time": 1673615253.1351264,
|
55 |
"auxillary_file_paths": [
|
56 |
+
"results/PushBlock Training/PushBlock/PushBlock-2000021.pt"
|
57 |
]
|
58 |
}
|
59 |
},
|