Load model

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:493e343e1a90092b1d5e64dfddc64fe3187257b9327686ab8446708eb0d34c2d
+size 1418184

Pyramids/Pyramids-1000023.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:493e343e1a90092b1d5e64dfddc64fe3187257b9327686ab8446708eb0d34c2d
+size 1418184

Pyramids/Pyramids-1000023.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ba34ec564fb538c138574719e3b080c07505f5de340e73107f2e51ad312ab59
+size 9997742

Pyramids/Pyramids-499897.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65366714aeb8b80afc0f1d73ffc28c88cd9a79421816141f09faf1cef531527c
+size 1418184

Pyramids/Pyramids-499897.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abeee44887783e6438221c8f2cbfd05b62287cea95dbc2d7f1791f8f67f947c4
+size 9997742

Pyramids/Pyramids-86200.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0564155756a8aba5af7f5a779eb8d364fbe658e37c244f3137d1580d0b109e6b
+size 1418184

Pyramids/Pyramids-86200.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef09585e761a93309d7731b0d5ecc54fa7a1ff61f40563058c4303b505e64ac4
+size 9997742

Pyramids/Pyramids-999895.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:493e343e1a90092b1d5e64dfddc64fe3187257b9327686ab8446708eb0d34c2d
+size 1418184

Pyramids/Pyramids-999895.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a89c62808ef38dc80153862b351a833c60ec5f4ca619976e81caf1979ab12bf
+size 9997742

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ba34ec564fb538c138574719e3b080c07505f5de340e73107f2e51ad312ab59
+size 9997742

Pyramids/events.out.tfevents.1694165518.MSI.17272.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47c1015e96c8ebe77042ed854f160f0ce0070e1ed18ad445addc286da40f5512
+size 288528

README.md

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

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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}}, "curiosity": {"gamma": 0.99, "strength": 0.02, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": null, "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,90 @@
+default_settings: null
+behaviors:
+  Pyramids:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.01
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    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
+      curiosity:
+        gamma: 0.99
+        strength: 0.02
+        network_settings:
+          normalize: false
+          hidden_units: 256
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+        learning_rate: 0.0003
+        encoding_size: null
+    init_path: null
+    keep_checkpoints: 5
+    even_checkpoints: false
+    max_steps: 1000000
+    time_horizon: 128
+    summary_freq: 30000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: null
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: Pyramids Training
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: true
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/timers.json

@@ -0,0 +1,368 @@
+{
+    "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.4699142575263977,
+            "min": 0.3891666531562805,
+            "max": 1.500190019607544,
+            "count": 33
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 14142.5390625,
+            "min": 11687.453125,
+            "max": 45509.765625,
+            "count": 33
+        },
+        "Pyramids.Step.mean": {
+            "value": 989986.0,
+            "min": 29952.0,
+            "max": 989986.0,
+            "count": 33
+        },
+        "Pyramids.Step.sum": {
+            "value": 989986.0,
+            "min": 29952.0,
+            "max": 989986.0,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.018810128793120384,
+            "min": -0.10927955061197281,
+            "max": -0.0012816793750971556,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -4.552051067352295,
+            "min": -26.33637237548828,
+            "max": -0.31401145458221436,
+            "count": 33
+        },
+        "Pyramids.Policy.CuriosityValueEstimate.mean": {
+            "value": 0.1656452715396881,
+            "min": 0.1590929478406906,
+            "max": 0.5021917223930359,
+            "count": 33
+        },
+        "Pyramids.Policy.CuriosityValueEstimate.sum": {
+            "value": 40.08615493774414,
+            "min": 38.341400146484375,
+            "max": 120.52601623535156,
+            "count": 33
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06635392671498255,
+            "min": 0.06497024932366871,
+            "max": 0.07246138155990259,
+            "count": 33
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9289549740097558,
+            "min": 0.4817415838474047,
+            "max": 1.0739379732192758,
+            "count": 33
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.0031029837457519555,
+            "min": 0.00011244172555845392,
+            "max": 0.003513037227047043,
+            "count": 33
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.043441772440527375,
+            "min": 0.001461742432259901,
+            "max": 0.0491825211786586,
+            "count": 33
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 7.737375992335715e-06,
+            "min": 7.737375992335715e-06,
+            "max": 0.00029515063018788575,
+            "count": 33
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 0.00010832326389270001,
+            "min": 0.00010832326389270001,
+            "max": 0.0031441946519352,
+            "count": 33
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10257909285714285,
+            "min": 0.10257909285714285,
+            "max": 0.19838354285714285,
+            "count": 33
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4361073,
+            "min": 1.3691136000000002,
+            "max": 2.3480648000000004,
+            "count": 33
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.00026765137642857157,
+            "min": 0.00026765137642857157,
+            "max": 0.00983851593142857,
+            "count": 33
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0037471192700000017,
+            "min": 0.0037471192700000017,
+            "max": 0.10483167351999999,
+            "count": 33
+        },
+        "Pyramids.Losses.CuriosityForwardLoss.mean": {
+            "value": 0.07584772152038348,
+            "min": 0.07543217037649205,
+            "max": 0.42585953099772406,
+            "count": 33
+        },
+        "Pyramids.Losses.CuriosityForwardLoss.sum": {
+            "value": 1.0618681012853688,
+            "min": 1.0560503852708887,
+            "max": 2.9810167169840684,
+            "count": 33
+        },
+        "Pyramids.Losses.CuriosityInverseLoss.mean": {
+            "value": 0.06941799885564495,
+            "min": 0.06183912462577046,
+            "max": 0.7221576714221455,
+            "count": 33
+        },
+        "Pyramids.Losses.CuriosityInverseLoss.sum": {
+            "value": 0.9718519839790294,
+            "min": 0.8657477447607864,
+            "max": 5.055103699955018,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 950.96875,
+            "min": 868.4411764705883,
+            "max": 999.0,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 30431.0,
+            "min": 15984.0,
+            "max": 32491.0,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": -0.5138813045341522,
+            "min": -1.0000000521540642,
+            "max": -0.22170592581524567,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": -16.44420174509287,
+            "min": -32.000001668930054,
+            "max": -7.538001477718353,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": -0.5138813045341522,
+            "min": -1.0000000521540642,
+            "max": -0.22170592581524567,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": -16.44420174509287,
+            "min": -32.000001668930054,
+            "max": -7.538001477718353,
+            "count": 33
+        },
+        "Pyramids.Policy.CuriosityReward.mean": {
+            "value": 1.5551242381334305,
+            "min": 1.442157154354979,
+            "max": 6.1382381450384855,
+            "count": 33
+        },
+        "Pyramids.Policy.CuriosityReward.sum": {
+            "value": 49.763975620269775,
+            "min": 44.36399610340595,
+            "max": 176.31472471356392,
+            "count": 33
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1694165513",
+        "python_version": "3.9.17 (main, Jul  5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "\\\\?\\C:\\Users\\Leonard\\anaconda3\\envs\\ml-agents\\Scripts\\mlagents-learn .\\config\\ppo\\Pyramids.yaml --run-id=Pyramids Training --force",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.11.0+cu113",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1694167332"
+    },
+    "total": 1819.0755296999998,
+    "count": 1,
+    "self": 0.010550699999839708,
+    "children": {
+        "run_training.setup": {
+            "total": 0.0960595999999998,
+            "count": 1,
+            "self": 0.0960595999999998
+        },
+        "TrainerController.start_learning": {
+            "total": 1818.9689194,
+            "count": 1,
+            "self": 1.1975100000179282,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 7.0293030000000005,
+                    "count": 1,
+                    "self": 7.0293030000000005
+                },
+                "TrainerController.advance": {
+                    "total": 1810.639066099982,
+                    "count": 63055,
+                    "self": 1.1738500999983899,
+                    "children": {
+                        "env_step": {
+                            "total": 959.0570887999919,
+                            "count": 63055,
+                            "self": 785.9034175999773,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 172.3645049000137,
+                                    "count": 63055,
+                                    "self": 3.497180999999017,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 168.8673239000147,
+                                            "count": 62564,
+                                            "self": 168.8673239000147
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.7891663000008791,
+                                    "count": 63055,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 1811.6397657000075,
+                                            "count": 63055,
+                                            "is_parallel": true,
+                                            "self": 1111.0342455000198,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.0010573000000002608,
+                                                    "count": 1,
+                                                    "is_parallel": true,
+                                                    "self": 0.00021849999999989933,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.0008388000000003615,
+                                                            "count": 8,
+                                                            "is_parallel": true,
+                                                            "self": 0.0008388000000003615
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 700.6044628999878,
+                                                    "count": 63055,
+                                                    "is_parallel": true,
+                                                    "self": 19.215686699962248,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 13.143204700019632,
+                                                            "count": 63055,
+                                                            "is_parallel": true,
+                                                            "self": 13.143204700019632
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 615.1939641000101,
+                                                            "count": 63055,
+                                                            "is_parallel": true,
+                                                            "self": 615.1939641000101
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 53.05160739999575,
+                                                            "count": 63055,
+                                                            "is_parallel": true,
+                                                            "self": 12.587725099981405,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 40.46388230001435,
+                                                                    "count": 504440,
+                                                                    "is_parallel": true,
+                                                                    "self": 40.46388230001435
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 850.4081271999918,
+                            "count": 63055,
+                            "self": 1.8936161999887418,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 100.93181030000363,
+                                    "count": 63055,
+                                    "self": 100.69354100000345,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.23826930000018365,
+                                            "count": 2,
+                                            "self": 0.23826930000018365
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 747.5827006999994,
+                                    "count": 430,
+                                    "self": 454.3094221999869,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 293.27327850001245,
+                                            "count": 22770,
+                                            "self": 293.27327850001245
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 7.999999525054591e-07,
+                    "count": 1,
+                    "self": 7.999999525054591e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.1030395000000226,
+                    "count": 1,
+                    "self": 0.007437600000002931,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.09560190000001967,
+                            "count": 1,
+                            "self": 0.09560190000001967
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,47 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 499897,
+                "file_path": "results\\Pyramids Training\\Pyramids\\Pyramids-499897.onnx",
+                "reward": -0.999800056219101,
+                "creation_time": 1694166428.7937474,
+                "auxillary_file_paths": [
+                    "results\\Pyramids Training\\Pyramids\\Pyramids-499897.pt"
+                ]
+            },
+            {
+                "steps": 999895,
+                "file_path": "results\\Pyramids Training\\Pyramids\\Pyramids-999895.onnx",
+                "reward": 1.791999951004982,
+                "creation_time": 1694167332.055924,
+                "auxillary_file_paths": [
+                    "results\\Pyramids Training\\Pyramids\\Pyramids-999895.pt"
+                ]
+            },
+            {
+                "steps": 1000023,
+                "file_path": "results\\Pyramids Training\\Pyramids\\Pyramids-1000023.onnx",
+                "reward": 1.791999951004982,
+                "creation_time": 1694167332.1625447,
+                "auxillary_file_paths": [
+                    "results\\Pyramids Training\\Pyramids\\Pyramids-1000023.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1000023,
+            "file_path": "results\\Pyramids Training\\Pyramids.onnx",
+            "reward": 1.791999951004982,
+            "creation_time": 1694167332.1625447,
+            "auxillary_file_paths": [
+                "results\\Pyramids Training\\Pyramids\\Pyramids-1000023.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu113"
+    }
+}