Second Push`

README.md

@@ -0,0 +1,35 @@
+---
+library_name: ml-agents
+tags:
+- SoccerTwos
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-SoccerTwos
+---
+
+  # **poca** Agent playing **SoccerTwos**
+  This is a trained model of a **poca** agent playing **SoccerTwos**
+  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: manuih/poca-SoccerTwos_basic
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

SoccerTwos/Basic_SoccerTwos-50000089.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfb4d2850adac54b4aec5bdb96ec3ef7315809f8c143a208ff3929988e8c8c0b
+size 1768747

SoccerTwos/SoccerTwos-24999985.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f97180b0691d3d7b2529863290146bc8ed195e35fe975c80df7e47220e80566d
+size 1768747

SoccerTwos/SoccerTwos-24999985.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8814acf004b46a3b8b3fd0ed2da4c699a83b392f1913c3be95c8d6bd060152dd
+size 28430025

SoccerTwos/SoccerTwos-25499986.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cef4866dcd3a35f7dd70dfbce89fcfe6be8ae2a2ce96e6e737f6c77e97b8f211
+size 1768747

SoccerTwos/SoccerTwos-25499986.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc03c7769ad12168ba9fc9f005b918430b642d59b14380e2260617ba6ed47208
+size 28430025

SoccerTwos/SoccerTwos-25999957.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1eada8fa58d22aa65138b2750cc618e85da2f8291c01616970d0769c54a7ca1
+size 1768747

SoccerTwos/SoccerTwos-25999957.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05b5ddcc8d5a5926297025de4578c30950eea1e8522ca2008cb86fa2f477f76d
+size 28430025

SoccerTwos/SoccerTwos-26499966.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3af06b5b287205488aa9d0c9799b5587dd2d21b8f20dd30f012958379325344f
+size 1768747

SoccerTwos/SoccerTwos-26499966.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b70d98da308b53fa3ca853f2b7a7cdc50a87ae7c4711b7c936ef1f07e46a69a
+size 28430025

SoccerTwos/SoccerTwos-26999983.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10b2093c51fc91b5ce5583cfa0922313e2220e15a38bea301cb964951d6cbf9d
+size 1768747

SoccerTwos/SoccerTwos-26999983.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5e6d220ae5bd2caa83d897fb49225d9faa41a2725415293e84c20544a7cf08d
+size 28430025

SoccerTwos/SoccerTwos-48499992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5fbdce5e24bfb8913e020aba04bd1d68749bc4defca2c22870f6fbd49426fff
+size 1768747

SoccerTwos/SoccerTwos-48499992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50050c6fe09484323736e3b3f2bb483fe48f16b2b16c351e68e974cec76dcb75
+size 28430025

SoccerTwos/SoccerTwos-48999967.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58ac86b34cdf243e68324abf5b3779756908f317909957c2ddd272fbd20ad933
+size 1768747

SoccerTwos/SoccerTwos-48999967.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca762b4c8ad9d00956c1992f0f69cead9a2e7cfdc76cb1887eb6cacf3d57a5fc
+size 28430025

SoccerTwos/SoccerTwos-49499946.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97bbe9695e5a5e889e011b252188441d6eadf0cd0af9c217f7c7266b3d0602ac
+size 1768747

SoccerTwos/SoccerTwos-49499946.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99f65c68d1f7ab6467fd58a9e868819be73660ee37fd7e6416c15547fa8162b1
+size 28430025

SoccerTwos/SoccerTwos-49999985.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfb4d2850adac54b4aec5bdb96ec3ef7315809f8c143a208ff3929988e8c8c0b
+size 1768747

SoccerTwos/SoccerTwos-49999985.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c553483c39a7c7e3c615238c4680fda6e4a9628fa7e0b042e1e4edff0716d6ca
+size 28430025

SoccerTwos/SoccerTwos-50000089.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d6ab8ccffc442c594edea7cc843e659e0cae75b1b9487de9628faef45205fd6
+size 28430025

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26c801953353b833ee5a5f957f1106435a70fc5adb9079b6aa27878d24adb1f8
+size 28428927

SoccerTwos/events.out.tfevents.1702404546.Data-Licious.66120.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e99da2e66357ffb65660aeed2af6e18f9bed336fed918bd144642157a624d50
+size 10666247

SoccerTwos/events.out.tfevents.1702488889.Data-Licious.18628.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50066f70f8c4751d20675ef772c227e8a01b59a70fa52ae6d3834f1bfba991bd
+size 21461

SoccerTwos/events.out.tfevents.1702489628.Data-Licious.3640.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea3d6c3931baac07aa361ac0688f35416f6e1b1ed49a9d9c3f03f9c667bc90bf
+size 134747

SoccerTwos/events.out.tfevents.1702490444.Data-Licious.31276.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b25da783006a40e4fa1400de701a83de9db26ab2f51b05c41319c812693b43a
+size 16815925

SoccerTwos/events.out.tfevents.1702740265.Data-Licious.22440.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7bb12af07b7abb229dcb01fde1c3fc88b6c3ceea3275e135a56494a822aa891
+size 4441884

SoccerTwos/events.out.tfevents.1702956449.Data-Licious.27016.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2249e9cd36cfdfe0024daad60a462175a235e09094c7ae6146ab7c436973f53
+size 19200543

SoccerTwos_basic.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfb4d2850adac54b4aec5bdb96ec3ef7315809f8c143a208ff3929988e8c8c0b
+size 1768747

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "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": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": null, "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "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": "SoccerTwos_basic", "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

@@ -0,0 +1,83 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      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: 50000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 50000
+      team_change: 200000
+      swap_steps: 2000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: null
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  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: SoccerTwos_basic
+  initialize_from: null
+  load_model: false
+  resume: true
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/timers.json

@@ -0,0 +1,368 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 1.4300297498703003,
+            "min": 1.2939000129699707,
+            "max": 1.5566500425338745,
+            "count": 1868
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 29836.140625,
+            "min": 22882.525390625,
+            "max": 34798.74609375,
+            "count": 1868
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 46.556603773584904,
+            "min": 32.557046979865774,
+            "max": 80.59677419354838,
+            "count": 1868
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19740.0,
+            "min": 14076.0,
+            "max": 20932.0,
+            "count": 1868
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1505.6478202822311,
+            "min": 1444.130187443437,
+            "max": 1529.8664604141977,
+            "count": 1868
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 319197.337899833,
+            "min": 176473.29914229224,
+            "max": 440870.4304579644,
+            "count": 1868
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 49999985.0,
+            "min": 31329827.0,
+            "max": 49999985.0,
+            "count": 1868
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 49999985.0,
+            "min": 31329827.0,
+            "max": 49999985.0,
+            "count": 1868
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.008808558806777,
+            "min": -0.12382835894823074,
+            "max": 0.07764289528131485,
+            "count": 1868
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -1.8586058616638184,
+            "min": -27.87138557434082,
+            "max": 18.059650421142578,
+            "count": 1868
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.007905821315944195,
+            "min": -0.12627680599689484,
+            "max": 0.07929305732250214,
+            "count": 1868
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -1.6681283712387085,
+            "min": -28.078716278076172,
+            "max": 18.072132110595703,
+            "count": 1868
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 1868
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 1868
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.05238862738225132,
+            "min": -0.39782429911265865,
+            "max": 0.3570304734366281,
+            "count": 1868
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 11.05400037765503,
+            "min": -85.13440001010895,
+            "max": 74.9763994216919,
+            "count": 1868
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.05238862738225132,
+            "min": -0.39782429911265865,
+            "max": 0.3570304734366281,
+            "count": 1868
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 11.05400037765503,
+            "min": -85.13440001010895,
+            "max": 74.9763994216919,
+            "count": 1868
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1868
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1868
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.016061648454827566,
+            "min": 0.010508424140668163,
+            "max": 0.02448746747104451,
+            "count": 907
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.016061648454827566,
+            "min": 0.010508424140668163,
+            "max": 0.02448746747104451,
+            "count": 907
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.1309850513935089,
+            "min": 0.09209257910648981,
+            "max": 0.14468998163938523,
+            "count": 907
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.1309850513935089,
+            "min": 0.09209257910648981,
+            "max": 0.14468998163938523,
+            "count": 907
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.13237753336628277,
+            "min": 0.09314731905857722,
+            "max": 0.14641447762648266,
+            "count": 907
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.13237753336628277,
+            "min": 0.09314731905857722,
+            "max": 0.14641447762648266,
+            "count": 907
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 907
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 907
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 907
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 907
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 907
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 907
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1702956406",
+        "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul  5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "C:\\Users\\emanu\\miniconda3\\envs\\mlagents7\\Scripts\\mlagents-learn config/poca/SoccerTwos.yaml --run-id=SoccerTwos_basic --resume",
+        "mlagents_version": "1.0.0",
+        "mlagents_envs_version": "1.0.0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.13.1+cu117",
+        "numpy_version": "1.23.1",
+        "end_time_seconds": "1703067697"
+    },
+    "total": 111290.63815800002,
+    "count": 1,
+    "self": 0.03311730004497804,
+    "children": {
+        "run_training.setup": {
+            "total": 0.20670419998350553,
+            "count": 1,
+            "self": 0.20670419998350553
+        },
+        "TrainerController.start_learning": {
+            "total": 111290.39833649999,
+            "count": 1,
+            "self": 38.79569911569706,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 44.43875170004321,
+                    "count": 95,
+                    "self": 44.43875170004321
+                },
+                "TrainerController.advance": {
+                    "total": 111206.97457958423,
+                    "count": 1319563,
+                    "self": 35.55578088664333,
+                    "children": {
+                        "env_step": {
+                            "total": 34387.63442577858,
+                            "count": 1319563,
+                            "self": 21669.21721950115,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 12694.31907998005,
+                                    "count": 1319563,
+                                    "self": 180.90979260933818,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 12513.409287370712,
+                                            "count": 2342978,
+                                            "self": 12513.409287370712
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 24.098126297380077,
+                                    "count": 1319563,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 111197.43400599252,
+                                            "count": 1319563,
+                                            "is_parallel": true,
+                                            "self": 93654.25793216252,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.20589109970023856,
+                                                    "count": 190,
+                                                    "is_parallel": true,
+                                                    "self": 0.039865299535449594,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.16602580016478896,
+                                                            "count": 760,
+                                                            "is_parallel": true,
+                                                            "self": 0.16602580016478896
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 17542.970182730292,
+                                                    "count": 1319563,
+                                                    "is_parallel": true,
+                                                    "self": 906.9769658251607,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 775.9321822029888,
+                                                            "count": 1319563,
+                                                            "is_parallel": true,
+                                                            "self": 775.9321822029888
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 12988.819363005052,
+                                                            "count": 1319563,
+                                                            "is_parallel": true,
+                                                            "self": 12988.819363005052
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 2871.241671697091,
+                                                            "count": 2639126,
+                                                            "is_parallel": true,
+                                                            "self": 553.706305623753,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 2317.535366073338,
+                                                                    "count": 10556504,
+                                                                    "is_parallel": true,
+                                                                    "self": 2317.535366073338
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 76783.784372919,
+                            "count": 1319563,
+                            "self": 291.84621213772334,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 23569.340994681785,
+                                    "count": 1319563,
+                                    "self": 23563.75128538179,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 5.589709299994865,
+                                            "count": 38,
+                                            "self": 5.589709299994865
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 52922.5971660995,
+                                    "count": 907,
+                                    "self": 2743.3453059984895,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 50179.25186010101,
+                                            "count": 27210,
+                                            "self": 50179.25186010101
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 2.700020559132099e-06,
+                    "count": 1,
+                    "self": 2.700020559132099e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.18930339999496937,
+                    "count": 1,
+                    "self": 0.05483280000044033,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.13447059999452904,
+                            "count": 1,
+                            "self": 0.13447059999452904
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 48499992,
+                "file_path": "results\\SoccerTwos_basic\\SoccerTwos\\SoccerTwos-48499992.onnx",
+                "reward": 0.0,
+                "creation_time": 1703060709.7950232,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos_basic\\SoccerTwos\\SoccerTwos-48499992.pt"
+                ]
+            },
+            {
+                "steps": 48999967,
+                "file_path": "results\\SoccerTwos_basic\\SoccerTwos\\SoccerTwos-48999967.onnx",
+                "reward": 0.0,
+                "creation_time": 1703063017.9380782,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos_basic\\SoccerTwos\\SoccerTwos-48999967.pt"
+                ]
+            },
+            {
+                "steps": 49499946,
+                "file_path": "results\\SoccerTwos_basic\\SoccerTwos\\SoccerTwos-49499946.onnx",
+                "reward": 0.0,
+                "creation_time": 1703065385.2247744,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos_basic\\SoccerTwos\\SoccerTwos-49499946.pt"
+                ]
+            },
+            {
+                "steps": 49999985,
+                "file_path": "results\\SoccerTwos_basic\\SoccerTwos\\SoccerTwos-49999985.onnx",
+                "reward": 0.0,
+                "creation_time": 1703067697.1909475,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos_basic\\SoccerTwos\\SoccerTwos-49999985.pt"
+                ]
+            },
+            {
+                "steps": 50000089,
+                "file_path": "results\\SoccerTwos_basic\\SoccerTwos\\SoccerTwos-50000089.onnx",
+                "reward": 0.0,
+                "creation_time": 1703067697.373553,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos_basic\\SoccerTwos\\SoccerTwos-50000089.pt"
+                ]
+            }
+        ],
+        "elo": 1506.524088697046,
+        "final_checkpoint": {
+            "steps": 50000089,
+            "file_path": "results\\SoccerTwos_basic\\SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1703067697.373553,
+            "auxillary_file_paths": [
+                "results\\SoccerTwos_basic\\SoccerTwos\\SoccerTwos-50000089.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.0.0",
+        "torch_version": "1.13.1+cu117"
+    }
+}