First push

Goalie.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:528fe324137bdefc11d9df1e354ad7332ccf89e147e81e1630e2fd2b2144e9d3
+size 2592006

Goalie/Goalie-1499980.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00ad4187d24ba32a1cb4211213ec9ca33b8c3673b689c62780dd40cd6b64a771
+size 2592006

Goalie/Goalie-1499980.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b0ebb5fee644cbcbcfb2777aef65c79ecb12ecd6a18ce8568e08d662482eabe
+size 32773832

Goalie/Goalie-1807818.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:528fe324137bdefc11d9df1e354ad7332ccf89e147e81e1630e2fd2b2144e9d3
+size 2592006

Goalie/Goalie-1807818.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2078a259efee484acea7aecdd1edfc10ff38d2c593a7e1b8216f530d2ddcddbe
+size 32773832

Goalie/Goalie-499419.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c602068819b97fd30d4e67ffa292827a62dc8f1e761dcd576500c323cb25eb98
+size 2592006

Goalie/Goalie-499419.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c72036980a75642f7e5d9078fcb440161b51df6ad897b8234f14f7eea9a733c
+size 32773714

Goalie/Goalie-999974.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d208149066546b2cbdd5dc275d4df7f34acf0afc5651460bf68dd215bf886dd
+size 2592006

Goalie/Goalie-999974.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b21e5a83916cbbae7958cf2969f95b0cdbb035e7002eaa2f3081f65d7b4162f
+size 32773714

Goalie/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:074530d75a0e425d5c5fed68f395cdbf32b1f613aa92204ffa14015f46de5e21
+size 32773360

Goalie/events.out.tfevents.1702974737.wkm0572l.17640.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04fe232bbbb85f35981575fc99b0e2d36b77b350830a095f1d37d4c732748bda
+size 878789

README.md

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

Striker.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:946847c50a17e2840a72382dc711f3fdcd0d97de14359f55803a7945f811f1fd
+size 1682731

Striker/Striker-1499979.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c591fe1c4c4ebdcb6ec249edc885bc6fa764eb3f77a0aa296f749d21da44e7d
+size 1682731

Striker/Striker-1499979.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78f5abe4f082023ffc70e96edbdb195d4dc584b7b05f6502c21a598f241f43ca
+size 27655842

Striker/Striker-1802718.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:946847c50a17e2840a72382dc711f3fdcd0d97de14359f55803a7945f811f1fd
+size 1682731

Striker/Striker-1802718.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8516c2db87188995f97de48da6ed7b1b22d9b66e72513be52b52c4d567df1b43
+size 27655842

Striker/Striker-499317.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5adf593f9c5f99684ad2fc36409bdf2a594b7a8407eb1e974c916b8ef9c3bc38
+size 1682731

Striker/Striker-499317.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc4403febc48a359528d6a19b13d57fdb776e5f6b2bf886ace3862a3f1bdea21
+size 27655718

Striker/Striker-999985.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:595a72b959b2229f57071d55522ad2ac455c8ec13b01054c80ccb843704a966c
+size 1682731

Striker/Striker-999985.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:353d639e252d1faf4aee5fb6782b0a804089344ac0d473fed3db3e42869fcb2b
+size 27655718

Striker/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0e73e1cc5ad60c39a640fd4739c76772a2f459e59e04cf4d7adf493e734a8bd
+size 27655222

Striker/events.out.tfevents.1702974737.wkm0572l.17640.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1b794a56df21ba4337fe15ff05d9e584eaf1a6425b5a7b5c8ec837b5e1b2f6d
+size 731996

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"Goalie": {"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": 30000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 1000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}, "Striker": {"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": 30000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 4000, "window": 10, "play_against_latest_model_ratio": 0.5, "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": "Proba", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,132 @@
+default_settings: null
+behaviors:
+  Goalie:
+    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: 30000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 50000
+      team_change: 200000
+      swap_steps: 1000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+  Striker:
+    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: 30000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 50000
+      team_change: 200000
+      swap_steps: 4000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      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: Proba
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/timers.json

@@ -0,0 +1,611 @@
+{
+    "name": "root",
+    "gauges": {
+        "Goalie.Policy.Entropy.mean": {
+            "value": 2.6350436210632324,
+            "min": 2.6350436210632324,
+            "max": 3.295673131942749,
+            "count": 180
+        },
+        "Goalie.Policy.Entropy.sum": {
+            "value": 25570.462890625,
+            "min": 21048.62109375,
+            "max": 376798.96875,
+            "count": 180
+        },
+        "Goalie.Environment.EpisodeLength.mean": {
+            "value": 56.851190476190474,
+            "min": 46.45891003460208,
+            "max": 999.0,
+            "count": 180
+        },
+        "Goalie.Environment.EpisodeLength.sum": {
+            "value": 9551.0,
+            "min": 9013.0,
+            "max": 110862.0,
+            "count": 180
+        },
+        "Goalie.Self-play.ELO.mean": {
+            "value": 780.0279731783617,
+            "min": 780.0279731783617,
+            "max": 1197.0217993396393,
+            "count": 178
+        },
+        "Goalie.Self-play.ELO.sum": {
+            "value": 131044.69949396476,
+            "min": 1118.4588168213602,
+            "max": 170427.22083595095,
+            "count": 178
+        },
+        "Goalie.Step.mean": {
+            "value": 1799995.0,
+            "min": 9571.0,
+            "max": 1799995.0,
+            "count": 180
+        },
+        "Goalie.Step.sum": {
+            "value": 1799995.0,
+            "min": 9571.0,
+            "max": 1799995.0,
+            "count": 180
+        },
+        "Goalie.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.6391041278839111,
+            "min": -0.6458126306533813,
+            "max": 0.07203566282987595,
+            "count": 180
+        },
+        "Goalie.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -107.36949157714844,
+            "min": -133.0373992919922,
+            "max": 1.2246062755584717,
+            "count": 180
+        },
+        "Goalie.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.6391041278839111,
+            "min": -0.6458126306533813,
+            "max": 0.07203566282987595,
+            "count": 180
+        },
+        "Goalie.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -107.36949157714844,
+            "min": -133.0373992919922,
+            "max": 1.2246062755584717,
+            "count": 180
+        },
+        "Goalie.Environment.CumulativeReward.mean": {
+            "value": 0.059623811895670814,
+            "min": 0.045828039333589865,
+            "max": 0.9996801018714905,
+            "count": 180
+        },
+        "Goalie.Environment.CumulativeReward.sum": {
+            "value": 10.016800398472697,
+            "min": 9.021400986239314,
+            "max": 10.917801141738892,
+            "count": 180
+        },
+        "Goalie.Policy.ExtrinsicReward.mean": {
+            "value": -0.9403761930408931,
+            "min": -0.954171972018536,
+            "max": 0.9996801018714905,
+            "count": 180
+        },
+        "Goalie.Policy.ExtrinsicReward.sum": {
+            "value": -157.98320043087006,
+            "min": -204.1928020119667,
+            "max": 9.996801018714905,
+            "count": 180
+        },
+        "Goalie.Environment.GroupCumulativeReward.mean": {
+            "value": -1.0,
+            "min": -1.0,
+            "max": 0.0,
+            "count": 180
+        },
+        "Goalie.Environment.GroupCumulativeReward.sum": {
+            "value": -168.0,
+            "min": -214.0,
+            "max": 0.0,
+            "count": 180
+        },
+        "Goalie.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 180
+        },
+        "Goalie.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 180
+        },
+        "Goalie.Losses.PolicyLoss.mean": {
+            "value": 0.016466737778197665,
+            "min": 0.012115506251575425,
+            "max": 0.02352036564067627,
+            "count": 86
+        },
+        "Goalie.Losses.PolicyLoss.sum": {
+            "value": 0.016466737778197665,
+            "min": 0.012115506251575425,
+            "max": 0.02352036564067627,
+            "count": 86
+        },
+        "Goalie.Losses.ValueLoss.mean": {
+            "value": 0.022342384917040665,
+            "min": 0.0004670941584966689,
+            "max": 0.033746559917926786,
+            "count": 86
+        },
+        "Goalie.Losses.ValueLoss.sum": {
+            "value": 0.022342384917040665,
+            "min": 0.0004670941584966689,
+            "max": 0.033746559917926786,
+            "count": 86
+        },
+        "Goalie.Losses.BaselineLoss.mean": {
+            "value": 0.02234272056569656,
+            "min": 0.0004670941584966689,
+            "max": 0.033895690863331156,
+            "count": 86
+        },
+        "Goalie.Losses.BaselineLoss.sum": {
+            "value": 0.02234272056569656,
+            "min": 0.0004670941584966689,
+            "max": 0.033895690863331156,
+            "count": 86
+        },
+        "Goalie.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 86
+        },
+        "Goalie.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 86
+        },
+        "Goalie.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 86
+        },
+        "Goalie.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 86
+        },
+        "Goalie.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 86
+        },
+        "Goalie.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 86
+        },
+        "Striker.Policy.Entropy.mean": {
+            "value": 2.3203654289245605,
+            "min": 2.2051618099212646,
+            "max": 3.295681953430176,
+            "count": 180
+        },
+        "Striker.Policy.Entropy.sum": {
+            "value": 23760.54296875,
+            "min": 15216.9345703125,
+            "max": 1400902.125,
+            "count": 180
+        },
+        "Striker.Environment.EpisodeLength.mean": {
+            "value": 50.415841584158414,
+            "min": 35.613138686131386,
+            "max": 999.0,
+            "count": 180
+        },
+        "Striker.Environment.EpisodeLength.sum": {
+            "value": 10184.0,
+            "min": 8382.0,
+            "max": 412654.0,
+            "count": 180
+        },
+        "Striker.Step.mean": {
+            "value": 1799842.0,
+            "min": 9512.0,
+            "max": 1799842.0,
+            "count": 180
+        },
+        "Striker.Step.sum": {
+            "value": 1799842.0,
+            "min": 9512.0,
+            "max": 1799842.0,
+            "count": 180
+        },
+        "Striker.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.6013904213905334,
+            "min": -0.16535364091396332,
+            "max": 0.6533077955245972,
+            "count": 180
+        },
+        "Striker.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 120.87947082519531,
+            "min": -4.340723991394043,
+            "max": 179.00633239746094,
+            "count": 180
+        },
+        "Striker.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.601508378982544,
+            "min": -0.16497276723384857,
+            "max": 0.6537038087844849,
+            "count": 180
+        },
+        "Striker.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 120.90318298339844,
+            "min": -4.237868785858154,
+            "max": 179.11483764648438,
+            "count": 180
+        },
+        "Striker.Environment.CumulativeReward.mean": {
+            "value": -0.04979403170094413,
+            "min": -0.9997200965881348,
+            "max": -0.035969343590448156,
+            "count": 180
+        },
+        "Striker.Environment.CumulativeReward.sum": {
+            "value": -10.00860037188977,
+            "min": -10.743601087480783,
+            "max": -9.09960101544857,
+            "count": 180
+        },
+        "Striker.Policy.ExtrinsicReward.mean": {
+            "value": 0.8502029683162917,
+            "min": -1.9994401931762695,
+            "max": 0.891693424351894,
+            "count": 180
+        },
+        "Striker.Policy.ExtrinsicReward.sum": {
+            "value": 170.89079663157463,
+            "min": -20.052401542663574,
+            "max": 244.32399827241898,
+            "count": 180
+        },
+        "Striker.Environment.GroupCumulativeReward.mean": {
+            "value": 0.949791041772757,
+            "min": 0.0,
+            "max": 0.9636321185279066,
+            "count": 180
+        },
+        "Striker.Environment.GroupCumulativeReward.sum": {
+            "value": 190.90799939632416,
+            "min": 0.0,
+            "max": 264.0352004766464,
+            "count": 180
+        },
+        "Striker.Self-play.ELO.mean": {
+            "value": 1754.8676722052517,
+            "min": 1220.241356428936,
+            "max": 1754.8676722052517,
+            "count": 174
+        },
+        "Striker.Self-play.ELO.sum": {
+            "value": 354483.26978546084,
+            "min": 2454.501043758067,
+            "max": 477024.1997551883,
+            "count": 174
+        },
+        "Striker.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 180
+        },
+        "Striker.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 180
+        },
+        "Striker.Losses.PolicyLoss.mean": {
+            "value": 0.016374270856613294,
+            "min": 0.011526005501703669,
+            "max": 0.02352414818791052,
+            "count": 85
+        },
+        "Striker.Losses.PolicyLoss.sum": {
+            "value": 0.016374270856613294,
+            "min": 0.011526005501703669,
+            "max": 0.02352414818791052,
+            "count": 85
+        },
+        "Striker.Losses.ValueLoss.mean": {
+            "value": 0.023624402284622193,
+            "min": 0.0006618854221111784,
+            "max": 0.0355209739257892,
+            "count": 85
+        },
+        "Striker.Losses.ValueLoss.sum": {
+            "value": 0.023624402284622193,
+            "min": 0.0006618854221111784,
+            "max": 0.0355209739257892,
+            "count": 85
+        },
+        "Striker.Losses.BaselineLoss.mean": {
+            "value": 0.02373644212881724,
+            "min": 0.0006652884049496304,
+            "max": 0.03594138734042644,
+            "count": 85
+        },
+        "Striker.Losses.BaselineLoss.sum": {
+            "value": 0.02373644212881724,
+            "min": 0.0006652884049496304,
+            "max": 0.03594138734042644,
+            "count": 85
+        },
+        "Striker.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 85
+        },
+        "Striker.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 85
+        },
+        "Striker.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 85
+        },
+        "Striker.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 85
+        },
+        "Striker.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 85
+        },
+        "Striker.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 85
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1702974733",
+        "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
+        "command_line_arguments": "/home/operario/anaconda3/envs/mlagents/bin/mlagents-learn ml-agents/config/poca/StrikersVsGoalie.yaml --run-id=Proba",
+        "mlagents_version": "1.0.0",
+        "mlagents_envs_version": "1.0.0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.1.1+cu121",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1702980564"
+    },
+    "total": 5831.547219161999,
+    "count": 1,
+    "self": 0.004055126997627667,
+    "children": {
+        "run_training.setup": {
+            "total": 0.010500086000320152,
+            "count": 1,
+            "self": 0.010500086000320152
+        },
+        "TrainerController.start_learning": {
+            "total": 5831.532663949001,
+            "count": 1,
+            "self": 5.20653796030183,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 5.0229465030006395,
+                    "count": 19,
+                    "self": 5.0229465030006395
+                },
+                "TrainerController.advance": {
+                    "total": 5821.1293753806995,
+                    "count": 360326,
+                    "self": 6.000143237119119,
+                    "children": {
+                        "env_step": {
+                            "total": 3709.103530842298,
+                            "count": 360326,
+                            "self": 3106.020965303721,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 599.6483402995009,
+                                    "count": 360326,
+                                    "self": 29.682954025429353,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 569.9653862740715,
+                                            "count": 685680,
+                                            "self": 569.9653862740715
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 3.434225239076113,
+                                    "count": 360325,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 5702.365667279509,
+                                            "count": 360325,
+                                            "is_parallel": true,
+                                            "self": 3209.9978119108673,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0012914009994346998,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.0003063059994019568,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.000985095000032743,
+                                                                    "count": 6,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.000985095000032743
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.020311455999944883,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0004727990008177585,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00023028099985822337,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00023028099985822337
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.01830136799981119,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.01830136799981119
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.00130700799945771,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0002533939996283152,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0010536139998293947,
+                                                                            "count": 6,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0010536139998293947
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 2492.3496092696414,
+                                                    "count": 360324,
+                                                    "is_parallel": true,
+                                                    "self": 116.63121924221014,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 65.49518589350373,
+                                                            "count": 360324,
+                                                            "is_parallel": true,
+                                                            "self": 65.49518589350373
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1983.5648633142227,
+                                                            "count": 360324,
+                                                            "is_parallel": true,
+                                                            "self": 1983.5648633142227
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 326.6583408197048,
+                                                            "count": 720648,
+                                                            "is_parallel": true,
+                                                            "self": 63.17436062367142,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 263.4839801960334,
+                                                                    "count": 2161944,
+                                                                    "is_parallel": true,
+                                                                    "self": 263.4839801960334
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.018246098999952665,
+                                                    "count": 36,
+                                                    "is_parallel": true,
+                                                    "self": 0.003693893993840902,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.014552205006111762,
+                                                            "count": 108,
+                                                            "is_parallel": true,
+                                                            "self": 0.014552205006111762
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 2106.0257013012824,
+                            "count": 720650,
+                            "self": 37.160836643673065,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 342.6532845196207,
+                                    "count": 720650,
+                                    "self": 341.9924087116178,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.6608758080028565,
+                                            "count": 6,
+                                            "self": 0.6608758080028565
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 1726.2115801379887,
+                                    "count": 173,
+                                    "self": 296.8522167799774,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 1429.3593633580113,
+                                            "count": 5190,
+                                            "self": 1429.3593633580113
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.1738041049993626,
+                    "count": 1,
+                    "self": 0.00232954700186383,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.17147455799749878,
+                            "count": 2,
+                            "self": 0.17147455799749878
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,107 @@
+{
+    "Goalie": {
+        "checkpoints": [
+            {
+                "steps": 499419,
+                "file_path": "results/Proba/Goalie/Goalie-499419.onnx",
+                "reward": 0.7520077661252939,
+                "creation_time": 1702976047.3382895,
+                "auxillary_file_paths": [
+                    "results/Proba/Goalie/Goalie-499419.pt"
+                ]
+            },
+            {
+                "steps": 999974,
+                "file_path": "results/Proba/Goalie/Goalie-999974.onnx",
+                "reward": 0.3689773957824932,
+                "creation_time": 1702977402.499321,
+                "auxillary_file_paths": [
+                    "results/Proba/Goalie/Goalie-999974.pt"
+                ]
+            },
+            {
+                "steps": 1499980,
+                "file_path": "results/Proba/Goalie/Goalie-1499980.onnx",
+                "reward": 0.042800000247855984,
+                "creation_time": 1702979254.7808285,
+                "auxillary_file_paths": [
+                    "results/Proba/Goalie/Goalie-1499980.pt"
+                ]
+            },
+            {
+                "steps": 1807818,
+                "file_path": "results/Proba/Goalie/Goalie-1807818.onnx",
+                "reward": null,
+                "creation_time": 1702980564.4739382,
+                "auxillary_file_paths": [
+                    "results/Proba/Goalie/Goalie-1807818.pt"
+                ]
+            }
+        ],
+        "elo": 771.3258240415493,
+        "final_checkpoint": {
+            "steps": 1807818,
+            "file_path": "results/Proba/Goalie.onnx",
+            "reward": null,
+            "creation_time": 1702980564.4739382,
+            "auxillary_file_paths": [
+                "results/Proba/Goalie/Goalie-1807818.pt"
+            ]
+        }
+    },
+    "Striker": {
+        "checkpoints": [
+            {
+                "steps": 499317,
+                "file_path": "results/Proba/Striker/Striker-499317.onnx",
+                "reward": -0.5727692818125854,
+                "creation_time": 1702976347.5755029,
+                "auxillary_file_paths": [
+                    "results/Proba/Striker/Striker-499317.pt"
+                ]
+            },
+            {
+                "steps": 999985,
+                "file_path": "results/Proba/Striker/Striker-999985.onnx",
+                "reward": -0.07280247349200057,
+                "creation_time": 1702977703.5105634,
+                "auxillary_file_paths": [
+                    "results/Proba/Striker/Striker-999985.pt"
+                ]
+            },
+            {
+                "steps": 1499979,
+                "file_path": "results/Proba/Striker/Striker-1499979.onnx",
+                "reward": -0.05407068019914896,
+                "creation_time": 1702979607.5258744,
+                "auxillary_file_paths": [
+                    "results/Proba/Striker/Striker-1499979.pt"
+                ]
+            },
+            {
+                "steps": 1802718,
+                "file_path": "results/Proba/Striker/Striker-1802718.onnx",
+                "reward": -0.03104210407228062,
+                "creation_time": 1702980564.5476835,
+                "auxillary_file_paths": [
+                    "results/Proba/Striker/Striker-1802718.pt"
+                ]
+            }
+        ],
+        "elo": 1755.7615527828686,
+        "final_checkpoint": {
+            "steps": 1802718,
+            "file_path": "results/Proba/Striker.onnx",
+            "reward": -0.03104210407228062,
+            "creation_time": 1702980564.5476835,
+            "auxillary_file_paths": [
+                "results/Proba/Striker/Striker-1802718.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.0.0",
+        "torch_version": "2.1.1+cu121"
+    }
+}