Pushing Unit 5 Pyramids1 model

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8119c613b2b885b2b46dca785a07376a22c7b832bfcc45f1908167d254f44c4
+size 1420238

Pyramids/Pyramids-0.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0658db6f81b9f303ea4f86e0970bd6ca133c892a043a4982ba3e942deb5ed705
+size 1418249

Pyramids/Pyramids-0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:781cc01a75034a1980268b4cc367117d362b59d25daefa0d645dd7604b253289
+size 2995554

Pyramids/Pyramids-1000012.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8119c613b2b885b2b46dca785a07376a22c7b832bfcc45f1908167d254f44c4
+size 1420238

Pyramids/Pyramids-1000012.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d61670d10b37b90efac3fa936c40464bfbb0742d79ae575689233a4b06b9d891
+size 8656252

Pyramids/Pyramids-499981.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:950c9d9a8741da24696dee281a070ad04914117688f26f0b9d299bca5634e84a
+size 1420238

Pyramids/Pyramids-499981.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e6dcd56533f76892721b2ff3d1ca3212e7825139aad0a01bc8f65de3d9d867d
+size 8656173

Pyramids/Pyramids-999884.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8119c613b2b885b2b46dca785a07376a22c7b832bfcc45f1908167d254f44c4
+size 1420238

Pyramids/Pyramids-999884.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44b560a5f54e77001c5c29fd501c31713c9ce21147c8ed4504c00e9f46999c43
+size 8656173

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e315e3e9d4878dfc818de50b2fbd3f39f106b339e3b64d0d05ec0c9c8f52259
+size 8655778

Pyramids/events.out.tfevents.1774334075.paul23.6488.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2854b0a97743dd6ce2135502ee302783712678d7467c8c79bf13d094550fee4
+size 313961

Pyramids/events.out.tfevents.1774351333.paul23.63896.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c76ca5249a5d96c21b8984b586dce625ffc33f4a2b1e538c7121f0b5fea12ee
+size 1423

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: rohit23/ppo-Pyramids-version001
+  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}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "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": "C:\\Users\\rohit\\Downloads\\RL-learn\\training-envs-executables\\windows\\Pyramids\\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": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids1", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": true, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,91 @@
+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
+      rnd:
+        gamma: 0.99
+        strength: 0.01
+        network_settings:
+          normalize: false
+          hidden_units: 64
+          num_layers: 3
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+        learning_rate: 0.0001
+        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: C:\Users\rohit\Downloads\RL-learn\training-envs-executables\windows\Pyramids\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: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: Pyramids1
+  initialize_from: null
+  load_model: false
+  resume: true
+  force: false
+  train_model: false
+  inference: true
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,42 @@
+Mono path[0] = 'C:/Users/rohit/Downloads/RL-learn/training-envs-executables/windows/Pyramids/UnityEnvironment_Data/Managed'
+Mono config path = 'C:/Users/rohit/Downloads/RL-learn/training-envs-executables/windows/Pyramids/MonoBleedingEdge/etc'
+CodeReloadManager initialized
+Input System module state changed to: Initialized.
+[Physics::Module] Initialized fallback backend.
+[Physics::Module] Id: 0xdecafbad
+Initialize engine version: 6000.4.0f1 (8cf496087c8f)
+[Subsystems] Discovering subsystems at path C:/Users/rohit/Downloads/RL-learn/training-envs-executables/windows/Pyramids/UnityEnvironment_Data/UnitySubsystems
+[D3D12 Device Filter] Vendor Name: NVIDIA
+[D3D12 Device Filter] Device Name: NVIDIA GeForce RTX 3050 6GB Laptop GPU
+[D3D12 Device Filter] Driver Version: 32.0.15.5585
+[D3D12 Device Filter] Feature Level: 12.2
+[D3D12 Device Filter] Graphics Memory: 6002 MB
+[D3D12 Device Filter] Processor Count: 12
+[D3D12 Device Filter] Device Type: Discrete
+GfxDevice: creating device client; kGfxThreadingModeThreaded
+Direct3D:
+    Version:  Direct3D 11.0 [level 11.1]
+    Renderer: NVIDIA GeForce RTX 3050 6GB Laptop GPU (ID=0x25ac)
+    Vendor:   NVIDIA
+    VRAM:     6002 MB
+    Driver:   32.0.15.5585
+Begin MonoManager ReloadAssembly
+- Finished resetting the current domain, in  0.002 seconds
+[Physics::Module] Selected backend.
+[Physics::Module] Name: PhysX
+[Physics::Module] Id: 0xf2b8ea05
+[Physics::Module] SDK Version: 4.1.2
+[Physics::Module] Integration Version: 1.0.0
+[Physics::Module] Threading Mode: Multi-Threaded
+<RI> Initializing input.
+Using Windows.Gaming.Input
+XInput1_3.dll not found. Trying XInput9_1_0.dll instead...
+<RI> Input initialized.
+UnloadTime: 0.645500 ms
+Registered Communicator in Agent.
+[Physics::Module] Cleanup current backend.
+[Physics::Module] Id: 0xf2b8ea05
+Input System module state changed to: ShutdownInProgress.
+Input Polling Thread exited.
+Input System module state changed to: Shutdown.
+CodeReloadManager destroyed

run_logs/timers.json

@@ -0,0 +1,143 @@
+{
+    "name": "root",
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1774351324",
+        "python_version": "3.10.11 | packaged by Anaconda, Inc. | (main, May 16 2023, 00:55:32) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "C:\\Users\\rohit\\miniconda3\\envs\\rl-learn\\Scripts\\mlagents-learn C:\\Users\\rohit\\Downloads\\RL-learn\\config\\ppo\\PyramidsRND.yaml --env=C:\\Users\\rohit\\Downloads\\RL-learn\\training-envs-executables\\windows\\Pyramids\\UnityEnvironment.exe --run-id=Pyramids1 --inference --resume",
+        "mlagents_version": "1.0.0",
+        "mlagents_envs_version": "1.1.0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.6.0+cu124",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1774351372"
+    },
+    "total": 48.87714009999763,
+    "count": 1,
+    "self": 10.006929499912076,
+    "children": {
+        "run_training.setup": {
+            "total": 0.1279296000720933,
+            "count": 1,
+            "self": 0.1279296000720933
+        },
+        "TrainerController.start_learning": {
+            "total": 38.74228100001346,
+            "count": 1,
+            "self": 0.029113499796949327,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 11.584887400036678,
+                    "count": 1,
+                    "self": 11.584887400036678
+                },
+                "TrainerController.advance": {
+                    "total": 27.128279200172983,
+                    "count": 1205,
+                    "self": 0.030219002277590334,
+                    "children": {
+                        "env_step": {
+                            "total": 24.78010079928208,
+                            "count": 1205,
+                            "self": 19.980615599779412,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 4.782365499762818,
+                                    "count": 1206,
+                                    "self": 0.1007295026211068,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 4.681635997141711,
+                                            "count": 1175,
+                                            "self": 4.681635997141711
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.017119699739851058,
+                                    "count": 1204,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 23.39705480169505,
+                                            "count": 1204,
+                                            "is_parallel": true,
+                                            "self": 11.783425701782107,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.0033790001180022955,
+                                                    "count": 2,
+                                                    "is_parallel": true,
+                                                    "self": 0.0006664003012701869,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.0027125998167321086,
+                                                            "count": 16,
+                                                            "is_parallel": true,
+                                                            "self": 0.0027125998167321086
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 11.61025009979494,
+                                                    "count": 1204,
+                                                    "is_parallel": true,
+                                                    "self": 0.3885261978721246,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 0.316357901901938,
+                                                            "count": 1204,
+                                                            "is_parallel": true,
+                                                            "self": 0.316357901901938
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 9.808723400346935,
+                                                            "count": 1204,
+                                                            "is_parallel": true,
+                                                            "self": 9.808723400346935
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 1.0966425996739417,
+                                                            "count": 1204,
+                                                            "is_parallel": true,
+                                                            "self": 0.2563022974645719,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.8403403022093698,
+                                                                    "count": 9632,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.8403403022093698
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 2.3179593986133114,
+                            "count": 1204,
+                            "self": 0.03145549667533487,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 2.2865039019379765,
+                                    "count": 1204,
+                                    "self": 2.2865039019379765
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 9.00006853044033e-07,
+                    "count": 1,
+                    "self": 9.00006853044033e-07
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,47 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 499981,
+                "file_path": "results\\Pyramids1\\Pyramids\\Pyramids-499981.onnx",
+                "reward": 1.364499993622303,
+                "creation_time": 1774335910.8615959,
+                "auxillary_file_paths": [
+                    "results\\Pyramids1\\Pyramids\\Pyramids-499981.pt"
+                ]
+            },
+            {
+                "steps": 999884,
+                "file_path": "results\\Pyramids1\\Pyramids\\Pyramids-999884.onnx",
+                "reward": 1.488333319624265,
+                "creation_time": 1774337884.5285158,
+                "auxillary_file_paths": [
+                    "results\\Pyramids1\\Pyramids\\Pyramids-999884.pt"
+                ]
+            },
+            {
+                "steps": 1000012,
+                "file_path": "results\\Pyramids1\\Pyramids\\Pyramids-1000012.onnx",
+                "reward": 1.488333319624265,
+                "creation_time": 1774337884.713831,
+                "auxillary_file_paths": [
+                    "results\\Pyramids1\\Pyramids\\Pyramids-1000012.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1000012,
+            "file_path": "results\\Pyramids1\\Pyramids.onnx",
+            "reward": 1.488333319624265,
+            "creation_time": 1774337884.713831,
+            "auxillary_file_paths": [
+                "results\\Pyramids1\\Pyramids\\Pyramids-1000012.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.0.0",
+        "torch_version": "2.6.0+cu124"
+    }
+}