First Push`

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+run_logs/Player-0.log filter=lfs diff=lfs merge=lfs -text

DungeonEscape.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bb983b62fa2bffb61544aeff58445e1d936cedc0f8a7832986360607b86a22c
+size 656306

DungeonEscape/DungeonEscape-18499986.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e1954cbcc02eaf55b7dbab3590c45093c602a3777a19339ae6d0401ba27fb47
+size 656306

DungeonEscape/DungeonEscape-18499986.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:310deff633f9a0d7cb618545f72942f01c858cdf7cf35b39896843cfbdca9b48
+size 9035830

DungeonEscape/DungeonEscape-18999978.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:121e831cc2c3c4f6a4b35bb0e703dae3955338271c156a0b66b720d55c1ac3d5
+size 656306

DungeonEscape/DungeonEscape-18999978.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b95169ff39ae92b2ac307daf218038d1e41a501aae8bccceb5348b4eb2e15241
+size 9035830

DungeonEscape/DungeonEscape-19499964.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9fc7ce89b1e81695cd2a82643576340ceb13425b5d6beb1dbec3ddece1dc952
+size 656306

DungeonEscape/DungeonEscape-19499964.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a67d976e94988737dfbed4c4993c24886fbf5ecad2eebe4ff9e497ca4ff08223
+size 9035830

DungeonEscape/DungeonEscape-19999974.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bb983b62fa2bffb61544aeff58445e1d936cedc0f8a7832986360607b86a22c
+size 656306

DungeonEscape/DungeonEscape-19999974.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e29a83b7c353db69ad8968255732ad1e3ce345dec8209e4d22ef5bbf3f67504d
+size 9035830

DungeonEscape/DungeonEscape-20000066.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bb983b62fa2bffb61544aeff58445e1d936cedc0f8a7832986360607b86a22c
+size 656306

DungeonEscape/DungeonEscape-20000066.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17534ef5d2beddbd39cc1c9f0265d6aefa79fcfb4d92d71c88d527a4082fdd0a
+size 9035830

DungeonEscape/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccf728d75f16ace88ebeef9afb62ef34cf5116781af2deff0e26460b6073e097
+size 9034406

DungeonEscape/events.out.tfevents.1734433832.DESKTOP-HLQ0VVT.4592.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:804e0ac7e6e7a76be13440ed1358bca0ba902c02f808f4056b51a560572147d8
+size 121263

DungeonEscape/events.out.tfevents.1734446706.DESKTOP-HLQ0VVT.4888.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b79659694e92cb8dd47dcfc53ceb2271812c0991540e03c3d536529f509365f3
+size 1790850

README.md

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

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"DungeonEscape": {"trainer_type": "poca", "hyperparameters": {"batch_size": 1024, "buffer_size": 10240, "learning_rate": 0.0003, "beta": 0.01, "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": 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": 64, "summary_freq": 60000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/DungeonEscape/UnityEnvironment.exe", "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": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "DungeonEscape", "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 +1,78 @@
+default_settings: null
+behaviors:
+  DungeonEscape:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 1024
+      buffer_size: 10240
+      learning_rate: 0.0003
+      beta: 0.01
+      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: 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: 64
+    summary_freq: 60000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/DungeonEscape/UnityEnvironment.exe
+  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: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: DungeonEscape
+  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/Player-0.log

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f88dabce5afa66411529e1281ea85352a56f2a428de3240d77b1b5686dd3795c
+size 594194735

run_logs/timers.json

@@ -0,0 +1,356 @@
+{
+    "name": "root",
+    "gauges": {
+        "DungeonEscape.Policy.Entropy.mean": {
+            "value": 0.7387705445289612,
+            "min": 0.47643986344337463,
+            "max": 0.963077187538147,
+            "count": 312
+        },
+        "DungeonEscape.Policy.Entropy.sum": {
+            "value": 44270.0859375,
+            "min": 19316.052734375,
+            "max": 57795.2265625,
+            "count": 312
+        },
+        "DungeonEscape.Environment.EpisodeLength.mean": {
+            "value": 29.690537084398976,
+            "min": 29.25568468923699,
+            "max": 51.92042440318303,
+            "count": 312
+        },
+        "DungeonEscape.Environment.EpisodeLength.sum": {
+            "value": 58045.0,
+            "min": 20170.0,
+            "max": 61799.0,
+            "count": 312
+        },
+        "DungeonEscape.Step.mean": {
+            "value": 19979994.0,
+            "min": 1319967.0,
+            "max": 19979994.0,
+            "count": 312
+        },
+        "DungeonEscape.Step.sum": {
+            "value": 19979994.0,
+            "min": 1319967.0,
+            "max": 19979994.0,
+            "count": 312
+        },
+        "DungeonEscape.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.7170155048370361,
+            "min": 0.4537115693092346,
+            "max": 0.7238806486129761,
+            "count": 312
+        },
+        "DungeonEscape.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 1488.524169921875,
+            "min": 291.70721435546875,
+            "max": 1514.08251953125,
+            "count": 312
+        },
+        "DungeonEscape.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.7190065979957581,
+            "min": 0.45914435386657715,
+            "max": 0.7242827415466309,
+            "count": 312
+        },
+        "DungeonEscape.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 1492.65771484375,
+            "min": 295.56463623046875,
+            "max": 1519.375,
+            "count": 312
+        },
+        "DungeonEscape.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 312
+        },
+        "DungeonEscape.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 312
+        },
+        "DungeonEscape.Policy.ExtrinsicReward.mean": {
+            "value": 0.6005115089514067,
+            "min": 0.42398884239888424,
+            "max": 0.618756936736959,
+            "count": 312
+        },
+        "DungeonEscape.Policy.ExtrinsicReward.sum": {
+            "value": 1174.0,
+            "min": 212.0,
+            "max": 1192.0,
+            "count": 312
+        },
+        "DungeonEscape.Environment.GroupCumulativeReward.mean": {
+            "value": 0.9072642967542504,
+            "min": 0.5705244122965641,
+            "max": 0.923777961888981,
+            "count": 312
+        },
+        "DungeonEscape.Environment.GroupCumulativeReward.sum": {
+            "value": 1174.0,
+            "min": 212.0,
+            "max": 1192.0,
+            "count": 312
+        },
+        "DungeonEscape.Losses.PolicyLoss.mean": {
+            "value": 0.025970765251097164,
+            "min": 0.02003467489654819,
+            "max": 0.02940388735021568,
+            "count": 312
+        },
+        "DungeonEscape.Losses.PolicyLoss.sum": {
+            "value": 0.15582459150658298,
+            "min": 0.04384033279493451,
+            "max": 0.17642332410129408,
+            "count": 312
+        },
+        "DungeonEscape.Losses.ValueLoss.mean": {
+            "value": 0.007493831320769257,
+            "min": 0.006882970143730442,
+            "max": 0.012657495976115266,
+            "count": 312
+        },
+        "DungeonEscape.Losses.ValueLoss.sum": {
+            "value": 0.04496298792461554,
+            "min": 0.025314991952230533,
+            "max": 0.07474336146066586,
+            "count": 312
+        },
+        "DungeonEscape.Losses.BaselineLoss.mean": {
+            "value": 0.0073994019935424956,
+            "min": 0.007087137286240855,
+            "max": 0.011768768857129743,
+            "count": 312
+        },
+        "DungeonEscape.Losses.BaselineLoss.sum": {
+            "value": 0.044396411961254975,
+            "min": 0.023281445292135078,
+            "max": 0.07061261314277846,
+            "count": 312
+        },
+        "DungeonEscape.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 312
+        },
+        "DungeonEscape.Policy.LearningRate.sum": {
+            "value": 0.0017999999999999997,
+            "min": 0.0006,
+            "max": 0.0017999999999999997,
+            "count": 312
+        },
+        "DungeonEscape.Policy.Epsilon.mean": {
+            "value": 0.2000000000000001,
+            "min": 0.20000000000000007,
+            "max": 0.2000000000000001,
+            "count": 312
+        },
+        "DungeonEscape.Policy.Epsilon.sum": {
+            "value": 1.2000000000000006,
+            "min": 0.40000000000000013,
+            "max": 1.2000000000000006,
+            "count": 312
+        },
+        "DungeonEscape.Policy.Beta.mean": {
+            "value": 0.010000000000000002,
+            "min": 0.010000000000000002,
+            "max": 0.010000000000000002,
+            "count": 312
+        },
+        "DungeonEscape.Policy.Beta.sum": {
+            "value": 0.06000000000000001,
+            "min": 0.020000000000000004,
+            "max": 0.06000000000000001,
+            "count": 312
+        },
+        "DungeonEscape.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 312
+        },
+        "DungeonEscape.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 312
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1734446699",
+        "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:\\anaconda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/DungeonEscape.yaml --env=./training-envs-executables/DungeonEscape/UnityEnvironment.exe --run-id=DungeonEscape --no-graphics --resume",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.5.1+cpu",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1734474139"
+    },
+    "total": 27436.995059499997,
+    "count": 1,
+    "self": 0.3181868999963626,
+    "children": {
+        "run_training.setup": {
+            "total": 0.1388437999994494,
+            "count": 1,
+            "self": 0.1388437999994494
+        },
+        "TrainerController.start_learning": {
+            "total": 27436.5380288,
+            "count": 1,
+            "self": 21.926181698567234,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 8.739799100001619,
+                    "count": 1,
+                    "self": 8.739799100001619
+                },
+                "TrainerController.advance": {
+                    "total": 27405.812782101428,
+                    "count": 948274,
+                    "self": 18.10939840339779,
+                    "children": {
+                        "env_step": {
+                            "total": 9457.995401397598,
+                            "count": 948274,
+                            "self": 8518.083113295848,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 927.308839501331,
+                                    "count": 948274,
+                                    "self": 53.046044098589846,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 874.2627954027412,
+                                            "count": 815033,
+                                            "self": 874.2627954027412
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 12.603448600419142,
+                                    "count": 948274,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 27404.168480200235,
+                                            "count": 948274,
+                                            "is_parallel": true,
+                                            "self": 20618.923279797527,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.005296400000588619,
+                                                    "count": 1,
+                                                    "is_parallel": true,
+                                                    "self": 0.0009778000003279885,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.004318600000260631,
+                                                            "count": 6,
+                                                            "is_parallel": true,
+                                                            "self": 0.004318600000260631
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 6785.239904002707,
+                                                    "count": 948274,
+                                                    "is_parallel": true,
+                                                    "self": 394.1696912051757,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 298.55590379998284,
+                                                            "count": 948274,
+                                                            "is_parallel": true,
+                                                            "self": 298.55590379998284
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 4872.826279197372,
+                                                            "count": 948274,
+                                                            "is_parallel": true,
+                                                            "self": 4872.826279197372
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 1219.688029800176,
+                                                            "count": 948274,
+                                                            "is_parallel": true,
+                                                            "self": 189.64897849756017,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 1030.039051302616,
+                                                                    "count": 5689644,
+                                                                    "is_parallel": true,
+                                                                    "self": 1030.039051302616
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 17929.70798230043,
+                            "count": 948274,
+                            "self": 40.4367261020634,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 5760.006832598403,
+                                    "count": 948274,
+                                    "self": 5757.721544298418,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 2.285288299985041,
+                                            "count": 38,
+                                            "self": 2.285288299985041
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 12129.264423599965,
+                                    "count": 1818,
+                                    "self": 3112.0907305996734,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 9017.173693000292,
+                                            "count": 54540,
+                                            "self": 9017.173693000292
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.0000003385357559e-06,
+                    "count": 1,
+                    "self": 1.0000003385357559e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.05926490000274498,
+                    "count": 1,
+                    "self": 0.0012898000059067272,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.05797509999683825,
+                            "count": 1,
+                            "self": 0.05797509999683825
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,65 @@
+{
+    "DungeonEscape": {
+        "checkpoints": [
+            {
+                "steps": 18499986,
+                "file_path": "results\\DungeonEscape\\DungeonEscape\\DungeonEscape-18499986.onnx",
+                "reward": 0.0,
+                "creation_time": 1734471898.69876,
+                "auxillary_file_paths": [
+                    "results\\DungeonEscape\\DungeonEscape\\DungeonEscape-18499986.pt"
+                ]
+            },
+            {
+                "steps": 18999978,
+                "file_path": "results\\DungeonEscape\\DungeonEscape\\DungeonEscape-18999978.onnx",
+                "reward": 0.0,
+                "creation_time": 1734472646.209435,
+                "auxillary_file_paths": [
+                    "results\\DungeonEscape\\DungeonEscape\\DungeonEscape-18999978.pt"
+                ]
+            },
+            {
+                "steps": 19499964,
+                "file_path": "results\\DungeonEscape\\DungeonEscape\\DungeonEscape-19499964.onnx",
+                "reward": 0.0,
+                "creation_time": 1734473389.4965262,
+                "auxillary_file_paths": [
+                    "results\\DungeonEscape\\DungeonEscape\\DungeonEscape-19499964.pt"
+                ]
+            },
+            {
+                "steps": 19999974,
+                "file_path": "results\\DungeonEscape\\DungeonEscape\\DungeonEscape-19999974.onnx",
+                "reward": 0.0,
+                "creation_time": 1734474138.6712694,
+                "auxillary_file_paths": [
+                    "results\\DungeonEscape\\DungeonEscape\\DungeonEscape-19999974.pt"
+                ]
+            },
+            {
+                "steps": 20000066,
+                "file_path": "results\\DungeonEscape\\DungeonEscape\\DungeonEscape-20000066.onnx",
+                "reward": 0.0,
+                "creation_time": 1734474138.7532325,
+                "auxillary_file_paths": [
+                    "results\\DungeonEscape\\DungeonEscape\\DungeonEscape-20000066.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 20000066,
+            "file_path": "results\\DungeonEscape\\DungeonEscape.onnx",
+            "reward": 0.0,
+            "creation_time": 1734474138.7532325,
+            "auxillary_file_paths": [
+                "results\\DungeonEscape\\DungeonEscape\\DungeonEscape-20000066.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.5.1+cpu"
+    }
+}