First Push

BigWallJump.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31a40b36dfed240c7ab2ba57aa6c496078212d7dcce94ff871bd09de7b02b491
+size 741938

BigWallJump/BigWallJump-18499991.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:999e5fdbec013154017a315698a8c432b1d8e9b12e6e9e4b29361bf753558a1f
+size 741938

BigWallJump/BigWallJump-18499991.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3922fcd20fc8804d94d77f6352c4ddc4dbcb0fc789f5938dbbec81c74de0bc78
+size 4377440

BigWallJump/BigWallJump-18999986.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c57fdebb3f3118ed94afa1461f1f6702330c1c05734be772da0500fd167ef49
+size 741938

BigWallJump/BigWallJump-18999986.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:951701de97ef08d512476638c9ac5cd0f94759301c44f213b6ff448da14b99a9
+size 4377440

BigWallJump/BigWallJump-19499996.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1687140d353e5427f859c4c3ea0fc5049a150481aa3e8b94cb2b913753aac535
+size 741938

BigWallJump/BigWallJump-19499996.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14846b956c6c839036ed3d4568c617518c949964f36153d0d5ffacac94170c9c
+size 4377440

BigWallJump/BigWallJump-19999998.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31a40b36dfed240c7ab2ba57aa6c496078212d7dcce94ff871bd09de7b02b491
+size 741938

BigWallJump/BigWallJump-19999998.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb21671ffd052eebd51e6d2a579e828e8ee91f112f611ee1959ce0025ff2ef45
+size 4377440

BigWallJump/BigWallJump-20000020.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31a40b36dfed240c7ab2ba57aa6c496078212d7dcce94ff871bd09de7b02b491
+size 741938

BigWallJump/BigWallJump-20000020.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ef98ec111fc668dd4ca1036a09508467d5753bb08534a75e66e39f6df3d6e48
+size 4377440

BigWallJump/BigWallJump-24803.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5caedf81c91eaf3eba503198dcb9ae508346f755c1cedc5ab2a07e6e9ef39e05
+size 741938

BigWallJump/BigWallJump-24803.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:261abf29a5acff0fab040c4afdc854d8e67e2eb54c2a5d799162a4a8ff185bf3
+size 4377191

BigWallJump/BigWallJump-39339.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb1ff0bb2c4488324597f0f507eedf260718b1272e2be32f2945e4c6719882fa
+size 741938

BigWallJump/BigWallJump-39339.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b32f22287fb2ca5023f14fb2060df26ececf1662fbe0aa018539dfcf4010b038
+size 4377191

BigWallJump/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59bd8db2cb7912688d88c27763ae8493f368dea3484b53d00bd3b668f8c4a546
+size 4376610

BigWallJump/events.out.tfevents.1693677309.yaohua-NUC12DCMi7.122030.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:972e7d53472beccca4f37a3e1186611f248ac066b63b4ab150bf859a24da88c5
+size 10113085

README.md

@@ -0,0 +1,35 @@
+---
+library_name: ml-agents
+tags:
+- BigWallJump
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-BigWallJump
+---
+
+  # **ppo** Agent playing **BigWallJump**
+  This is a trained model of a **ppo** agent playing **BigWallJump**
+  using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
+
+  ## Usage (with ML-Agents)
+  The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
+
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
+  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
+  - A *longer tutorial* to understand how works ML-Agents:
+  https://huggingface.co/learn/deep-rl-course/unit5/introduction
+
+  ### Resume the training
+  ```bash
+  mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
+  ```
+
+  ### Watch your Agent play
+  You can watch your agent **playing directly in your browser**
+
+  1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
+  2. Step 1: Find your model_id: yaohuacn/walljump_test_02
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

SmallWallJump.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ac7e842133d1d95145f1aa3c6fbf2dac4b0def184bbce5f8500359172957348
+size 741938

SmallWallJump/SmallWallJump-17209.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6aa8c6291f8bab28dfb8ba5017e1aca82fa9eadd1624450507033be7da8cdc8
+size 741938

SmallWallJump/SmallWallJump-17209.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:761179a5902d65978d60a01ca0d5f06a73365e52ecdb7640c4e3b767bceacad4
+size 4377357

SmallWallJump/SmallWallJump-17576.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9941ae401d7528ee4bb588d0b1e2d90a1dc3ee3f4296e85d32d7199c2d720869
+size 741938

SmallWallJump/SmallWallJump-17576.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f7676a4850568be437295d22e1a2499469d3c2bd7af14e4775fda8bebd5ce67
+size 4377357

SmallWallJump/SmallWallJump-3999997.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0801d7a093fff5c5d3cc78ac62d60f323481ebffb98fd5dd9f2ce3ac7cf1cf90
+size 741938

SmallWallJump/SmallWallJump-3999997.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79967437cfd06f9d9506705d97abfbfe8029c8f3af916679585199631e801a50
+size 4377523

SmallWallJump/SmallWallJump-4499998.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b6de973302486bf8b70b24e909b5829f4011407dcef0387fc977dd2a5293a2e
+size 741938

SmallWallJump/SmallWallJump-4499998.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77464c6bd8300540cf6bbf16bf5f470f9ab5d697a329cc4db72c05077259d53a
+size 4377523

SmallWallJump/SmallWallJump-4999999.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ac7e842133d1d95145f1aa3c6fbf2dac4b0def184bbce5f8500359172957348
+size 741938

SmallWallJump/SmallWallJump-4999999.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f16cc083805d04832936686e4b79083012c3583a258c20dee49a7c12120c716
+size 4377523

SmallWallJump/SmallWallJump-5499990.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ac7e842133d1d95145f1aa3c6fbf2dac4b0def184bbce5f8500359172957348
+size 741938

SmallWallJump/SmallWallJump-5499990.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e437711650f830f9c24003f722b8ad9f1643dc096c088122f15322a710fd9ca2
+size 4377523

SmallWallJump/SmallWallJump-5556184.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ac7e842133d1d95145f1aa3c6fbf2dac4b0def184bbce5f8500359172957348
+size 741938

SmallWallJump/SmallWallJump-5556184.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fda7b8d42a477a77ecb057336760664778e12f7357825161c16ea1a7dd4902c1
+size 4377523

SmallWallJump/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c37f3d482e0dff43cbdc55882a90ed1930e1e04f39114bcef9e07593df3f22f7
+size 4376610

SmallWallJump/events.out.tfevents.1693677307.yaohua-NUC12DCMi7.122030.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:793b770078255796f7c47dbafa509a785c2a91d606a17aebc63a9698f5e42d87
+size 2786054

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"BigWallJump": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 1024, "buffer_size": 4096, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "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, "even_checkpoints": false, "max_steps": 20000000, "time_horizon": 128, "summary_freq": 20000, "threaded": false, "self_play": null, "behavioral_cloning": null}, "SmallWallJump": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 1024, "buffer_size": 4096, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "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, "even_checkpoints": false, "max_steps": 5000000, "time_horizon": 128, "summary_freq": 20000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": null, "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": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "walljump_test_02", "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

@@ -0,0 +1,121 @@
+default_settings: null
+behaviors:
+  BigWallJump:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 1024
+      buffer_size: 4096
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 500000
+    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
+    even_checkpoints: false
+    max_steps: 20000000
+    time_horizon: 128
+    summary_freq: 20000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+  SmallWallJump:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 1024
+      buffer_size: 4096
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 500000
+    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
+    even_checkpoints: false
+    max_steps: 5000000
+    time_horizon: 128
+    summary_freq: 20000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: null
+  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: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: walljump_test_02
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: true
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/timers.json

@@ -0,0 +1,506 @@
+{
+    "name": "root",
+    "gauges": {
+        "BigWallJump.Policy.Entropy.mean": {
+            "value": 0.9725682139396667,
+            "min": 0.9625186920166016,
+            "max": 3.9519944190979004,
+            "count": 1000
+        },
+        "BigWallJump.Policy.Entropy.sum": {
+            "value": 19416.3515625,
+            "min": 19233.048828125,
+            "max": 82067.1171875,
+            "count": 1000
+        },
+        "BigWallJump.Environment.EpisodeLength.mean": {
+            "value": 24.652564102564103,
+            "min": 24.180100755667507,
+            "max": 360.2857142857143,
+            "count": 1000
+        },
+        "BigWallJump.Environment.EpisodeLength.sum": {
+            "value": 19229.0,
+            "min": 17869.0,
+            "max": 22004.0,
+            "count": 1000
+        },
+        "BigWallJump.Step.mean": {
+            "value": 19999998.0,
+            "min": 19986.0,
+            "max": 19999998.0,
+            "count": 1000
+        },
+        "BigWallJump.Step.sum": {
+            "value": 19999998.0,
+            "min": 19986.0,
+            "max": 19999998.0,
+            "count": 1000
+        },
+        "BigWallJump.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.8230504989624023,
+            "min": -0.5544101595878601,
+            "max": 0.8362411856651306,
+            "count": 1000
+        },
+        "BigWallJump.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 641.9793701171875,
+            "min": -146.78138732910156,
+            "max": 659.5391235351562,
+            "count": 1000
+        },
+        "BigWallJump.Environment.CumulativeReward.mean": {
+            "value": 0.8793814066128853,
+            "min": -1.2468177382446204,
+            "max": 0.9177374817593565,
+            "count": 1000
+        },
+        "BigWallJump.Environment.CumulativeReward.sum": {
+            "value": 685.9174971580505,
+            "min": -337.0195025871508,
+            "max": 719.9999975562096,
+            "count": 1000
+        },
+        "BigWallJump.Policy.ExtrinsicReward.mean": {
+            "value": 0.8793814066128853,
+            "min": -1.2468177382446204,
+            "max": 0.9177374817593565,
+            "count": 1000
+        },
+        "BigWallJump.Policy.ExtrinsicReward.sum": {
+            "value": 685.9174971580505,
+            "min": -337.0195025871508,
+            "max": 719.9999975562096,
+            "count": 1000
+        },
+        "BigWallJump.Losses.PolicyLoss.mean": {
+            "value": 0.017277905321680005,
+            "min": 0.013837956769081453,
+            "max": 0.03131256672592523,
+            "count": 1000
+        },
+        "BigWallJump.Losses.PolicyLoss.sum": {
+            "value": 0.08638952660840003,
+            "min": 0.06026011286303401,
+            "max": 0.15406981386089075,
+            "count": 1000
+        },
+        "BigWallJump.Losses.ValueLoss.mean": {
+            "value": 0.02471310798233996,
+            "min": 0.002555308794399025,
+            "max": 0.08699909243732691,
+            "count": 1000
+        },
+        "BigWallJump.Losses.ValueLoss.sum": {
+            "value": 0.1235655399116998,
+            "min": 0.0102212351775961,
+            "max": 0.43499546218663454,
+            "count": 1000
+        },
+        "BigWallJump.Policy.LearningRate.mean": {
+            "value": 1.7335894224700115e-07,
+            "min": 1.7335894224700115e-07,
+            "max": 0.0002998448963017012,
+            "count": 1000
+        },
+        "BigWallJump.Policy.LearningRate.sum": {
+            "value": 8.667947112350057e-07,
+            "min": 8.667947112350057e-07,
+            "max": 0.001497824085725305,
+            "count": 1000
+        },
+        "BigWallJump.Policy.Epsilon.mean": {
+            "value": 0.100057753,
+            "min": 0.100057753,
+            "max": 0.19994829875000003,
+            "count": 1000
+        },
+        "BigWallJump.Policy.Epsilon.sum": {
+            "value": 0.500288765,
+            "min": 0.400600675,
+            "max": 0.999274695,
+            "count": 1000
+        },
+        "BigWallJump.Policy.Beta.mean": {
+            "value": 1.2881874700000022e-05,
+            "min": 1.2881874700000022e-05,
+            "max": 0.004997420107625,
+            "count": 1000
+        },
+        "BigWallJump.Policy.Beta.sum": {
+            "value": 6.44093735000001e-05,
+            "min": 6.44093735000001e-05,
+            "max": 0.024963807280500003,
+            "count": 1000
+        },
+        "BigWallJump.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1000
+        },
+        "BigWallJump.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1000
+        },
+        "SmallWallJump.Policy.Entropy.mean": {
+            "value": 1.1432201862335205,
+            "min": 1.127864122390747,
+            "max": 3.9578561782836914,
+            "count": 277
+        },
+        "SmallWallJump.Policy.Entropy.sum": {
+            "value": 22802.669921875,
+            "min": 22546.00390625,
+            "max": 80419.6796875,
+            "count": 277
+        },
+        "SmallWallJump.Environment.EpisodeLength.mean": {
+            "value": 14.281130634071811,
+            "min": 13.952914798206278,
+            "max": 78.04247104247104,
+            "count": 277
+        },
+        "SmallWallJump.Environment.EpisodeLength.sum": {
+            "value": 18694.0,
+            "min": 18662.0,
+            "max": 20213.0,
+            "count": 277
+        },
+        "SmallWallJump.Step.mean": {
+            "value": 5539990.0,
+            "min": 19906.0,
+            "max": 5539990.0,
+            "count": 277
+        },
+        "SmallWallJump.Step.sum": {
+            "value": 5539990.0,
+            "min": 19906.0,
+            "max": 5539990.0,
+            "count": 277
+        },
+        "SmallWallJump.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.9011476635932922,
+            "min": -0.4881293773651123,
+            "max": 0.9083206057548523,
+            "count": 277
+        },
+        "SmallWallJump.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 1179.602294921875,
+            "min": -156.6895294189453,
+            "max": 1206.5859375,
+            "count": 277
+        },
+        "SmallWallJump.Environment.CumulativeReward.mean": {
+            "value": 0.9520741039965334,
+            "min": -1.0653809613504563,
+            "max": 0.9619308807722704,
+            "count": 277
+        },
+        "SmallWallJump.Environment.CumulativeReward.sum": {
+            "value": 1246.265002131462,
+            "min": -357.96800301375333,
+            "max": 1280.3300023078918,
+            "count": 277
+        },
+        "SmallWallJump.Policy.ExtrinsicReward.mean": {
+            "value": 0.9520741039965334,
+            "min": -1.0653809613504563,
+            "max": 0.9619308807722704,
+            "count": 277
+        },
+        "SmallWallJump.Policy.ExtrinsicReward.sum": {
+            "value": 1246.265002131462,
+            "min": -357.96800301375333,
+            "max": 1280.3300023078918,
+            "count": 277
+        },
+        "SmallWallJump.Losses.PolicyLoss.mean": {
+            "value": 0.020284520431111255,
+            "min": 0.014728642107608417,
+            "max": 0.027711384867628412,
+            "count": 250
+        },
+        "SmallWallJump.Losses.PolicyLoss.sum": {
+            "value": 0.10142260215555628,
+            "min": 0.06312889838591218,
+            "max": 0.13855692433814207,
+            "count": 250
+        },
+        "SmallWallJump.Losses.ValueLoss.mean": {
+            "value": 0.014050534221072062,
+            "min": 0.004349971085321158,
+            "max": 0.12879822564621765,
+            "count": 250
+        },
+        "SmallWallJump.Losses.ValueLoss.sum": {
+            "value": 0.0702526711053603,
+            "min": 0.0178363644372439,
+            "max": 0.6439911282310883,
+            "count": 250
+        },
+        "SmallWallJump.Policy.LearningRate.mean": {
+            "value": 5.532878156039934e-07,
+            "min": 5.532878156039934e-07,
+            "max": 0.00029937621020793,
+            "count": 250
+        },
+        "SmallWallJump.Policy.LearningRate.sum": {
+            "value": 2.7664390780199667e-06,
+            "min": 2.7664390780199667e-06,
+            "max": 0.00149128866290378,
+            "count": 250
+        },
+        "SmallWallJump.Policy.Epsilon.mean": {
+            "value": 0.100184396,
+            "min": 0.100184396,
+            "max": 0.19979207000000002,
+            "count": 250
+        },
+        "SmallWallJump.Policy.Epsilon.sum": {
+            "value": 0.50092198,
+            "min": 0.40878648000000006,
+            "max": 0.9970962200000001,
+            "count": 250
+        },
+        "SmallWallJump.Policy.Beta.mean": {
+            "value": 1.9201360399999894e-05,
+            "min": 1.9201360399999894e-05,
+            "max": 0.004989624293,
+            "count": 250
+        },
+        "SmallWallJump.Policy.Beta.sum": {
+            "value": 9.600680199999947e-05,
+            "min": 9.600680199999947e-05,
+            "max": 0.024855101378000004,
+            "count": 250
+        },
+        "SmallWallJump.IsTraining.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 1.0,
+            "count": 277
+        },
+        "SmallWallJump.IsTraining.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 1.0,
+            "count": 277
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1693677305",
+        "python_version": "3.10.10 (main, Mar 21 2023, 18:45:11) [GCC 11.2.0]",
+        "command_line_arguments": "/home/yaohua/miniconda3/envs/drl2/bin/mlagents-learn config/ppo/WallJump.yaml --run-id=walljump_test_02 --force",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.1.0.dev20230902+cu121",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1693694847"
+    },
+    "total": 17542.104710366002,
+    "count": 1,
+    "self": 0.0042794360051630065,
+    "children": {
+        "run_training.setup": {
+            "total": 0.2931904069992015,
+            "count": 1,
+            "self": 0.2931904069992015
+        },
+        "TrainerController.start_learning": {
+            "total": 17541.807240522998,
+            "count": 1,
+            "self": 23.918419953661214,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 4.204136708998703,
+                    "count": 1,
+                    "self": 4.204136708998703
+                },
+                "TrainerController.advance": {
+                    "total": 17513.588606540332,
+                    "count": 1649473,
+                    "self": 25.197562763569294,
+                    "children": {
+                        "env_step": {
+                            "total": 12823.833156169661,
+                            "count": 1649473,
+                            "self": 9685.534935636744,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 3124.260964101806,
+                                    "count": 1649473,
+                                    "self": 82.05208733542531,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 3042.208876766381,
+                                            "count": 2084685,
+                                            "self": 3042.208876766381
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 14.037256431111018,
+                                    "count": 1649473,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 17510.696612694024,
+                                            "count": 1649473,
+                                            "is_parallel": true,
+                                            "self": 9345.517714997717,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0019906219968106598,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.00035755999124376103,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0016330620055668987,
+                                                                    "count": 12,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0016330620055668987
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.015547777999017853,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00021877400286030024,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00022080600319895893,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00022080600319895893
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.014489156994386576,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.014489156994386576
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.000619040998572018,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00011063999409088865,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0005084010044811293,
+                                                                            "count": 12,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0005084010044811293
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 8165.178897696307,
+                                                    "count": 1649472,
+                                                    "is_parallel": true,
+                                                    "self": 376.3883987422014,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 164.2484304461541,
+                                                            "count": 1649472,
+                                                            "is_parallel": true,
+                                                            "self": 164.2484304461541
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 6517.66026597649,
+                                                            "count": 1649472,
+                                                            "is_parallel": true,
+                                                            "self": 6517.66026597649
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 1106.8818025314613,
+                                                            "count": 3298944,
+                                                            "is_parallel": true,
+                                                            "self": 223.7129027638657,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 883.1688997675956,
+                                                                    "count": 19793664,
+                                                                    "is_parallel": true,
+                                                                    "self": 883.1688997675956
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 4664.557887607101,
+                            "count": 3298946,
+                            "self": 64.85026829431445,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 1843.857758643273,
+                                    "count": 3298946,
+                                    "self": 1841.3516648222503,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 2.5060938210226595,
+                                            "count": 51,
+                                            "self": 2.5060938210226595
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 2755.849860669514,
+                                    "count": 6056,
+                                    "self": 2171.7557627543065,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 584.0940979152074,
+                                            "count": 72672,
+                                            "self": 584.0940979152074
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 5.440015229396522e-07,
+                    "count": 1,
+                    "self": 5.440015229396522e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.09607677600433817,
+                    "count": 1,
+                    "self": 0.0014533749999827705,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.0946234010043554,
+                            "count": 2,
+                            "self": 0.0946234010043554
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,123 @@
+{
+    "BigWallJump": {
+        "checkpoints": [
+            {
+                "steps": 18499991,
+                "file_path": "results/walljump_test_02/BigWallJump/BigWallJump-18499991.onnx",
+                "reward": 0.9090624977099268,
+                "creation_time": 1693693410.7455392,
+                "auxillary_file_paths": [
+                    "results/walljump_test_02/BigWallJump/BigWallJump-18499991.pt"
+                ]
+            },
+            {
+                "steps": 18999986,
+                "file_path": "results/walljump_test_02/BigWallJump/BigWallJump-18999986.onnx",
+                "reward": 0.8938157878423992,
+                "creation_time": 1693693892.4702873,
+                "auxillary_file_paths": [
+                    "results/walljump_test_02/BigWallJump/BigWallJump-18999986.pt"
+                ]
+            },
+            {
+                "steps": 19499996,
+                "file_path": "results/walljump_test_02/BigWallJump/BigWallJump-19499996.onnx",
+                "reward": 0.8163281232118607,
+                "creation_time": 1693694371.794366,
+                "auxillary_file_paths": [
+                    "results/walljump_test_02/BigWallJump/BigWallJump-19499996.pt"
+                ]
+            },
+            {
+                "steps": 19999998,
+                "file_path": "results/walljump_test_02/BigWallJump/BigWallJump-19999998.onnx",
+                "reward": 0.861711534170004,
+                "creation_time": 1693694847.2846408,
+                "auxillary_file_paths": [
+                    "results/walljump_test_02/BigWallJump/BigWallJump-19999998.pt"
+                ]
+            },
+            {
+                "steps": 20000020,
+                "file_path": "results/walljump_test_02/BigWallJump/BigWallJump-20000020.onnx",
+                "reward": 0.8623664078821662,
+                "creation_time": 1693694847.3825753,
+                "auxillary_file_paths": [
+                    "results/walljump_test_02/BigWallJump/BigWallJump-20000020.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 20000020,
+            "file_path": "results/walljump_test_02/BigWallJump.onnx",
+            "reward": 0.8623664078821662,
+            "creation_time": 1693694847.3825753,
+            "auxillary_file_paths": [
+                "results/walljump_test_02/BigWallJump/BigWallJump-20000020.pt"
+            ]
+        }
+    },
+    "SmallWallJump": {
+        "checkpoints": [
+            {
+                "steps": 3999997,
+                "file_path": "results/walljump_test_02/SmallWallJump/SmallWallJump-3999997.onnx",
+                "reward": 0.9061571420942034,
+                "creation_time": 1693690913.70728,
+                "auxillary_file_paths": [
+                    "results/walljump_test_02/SmallWallJump/SmallWallJump-3999997.pt"
+                ]
+            },
+            {
+                "steps": 4499998,
+                "file_path": "results/walljump_test_02/SmallWallJump/SmallWallJump-4499998.onnx",
+                "reward": 0.962499999198593,
+                "creation_time": 1693692202.4956467,
+                "auxillary_file_paths": [
+                    "results/walljump_test_02/SmallWallJump/SmallWallJump-4499998.pt"
+                ]
+            },
+            {
+                "steps": 4999999,
+                "file_path": "results/walljump_test_02/SmallWallJump/SmallWallJump-4999999.onnx",
+                "reward": 0.9641923088293809,
+                "creation_time": 1693693486.5171535,
+                "auxillary_file_paths": [
+                    "results/walljump_test_02/SmallWallJump/SmallWallJump-4999999.pt"
+                ]
+            },
+            {
+                "steps": 5499990,
+                "file_path": "results/walljump_test_02/SmallWallJump/SmallWallJump-5499990.onnx",
+                "reward": 0.9516337079151407,
+                "creation_time": 1693694711.5314128,
+                "auxillary_file_paths": [
+                    "results/walljump_test_02/SmallWallJump/SmallWallJump-5499990.pt"
+                ]
+            },
+            {
+                "steps": 5556184,
+                "file_path": "results/walljump_test_02/SmallWallJump/SmallWallJump-5556184.onnx",
+                "reward": 0.9514973373853384,
+                "creation_time": 1693694847.3359807,
+                "auxillary_file_paths": [
+                    "results/walljump_test_02/SmallWallJump/SmallWallJump-5556184.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 5556184,
+            "file_path": "results/walljump_test_02/SmallWallJump.onnx",
+            "reward": 0.9514973373853384,
+            "creation_time": 1693694847.3359807,
+            "auxillary_file_paths": [
+                "results/walljump_test_02/SmallWallJump/SmallWallJump-5556184.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "2.1.0.dev20230902+cu121"
+    }
+}