Pyramids model

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33590ede21dd0083b79de4702a2fb42aab48fa0ceac5a818fb217683b9623ca4
+size 1418184

README.md

@@ -0,0 +1,29 @@
+---
+library_name: ml-agents
+tags:
+- Pyramids
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-Pyramids
+- curiosity
+- RND
+---
+
+# **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).
+
+This agent uses **Random Network Distillation (RND)** for curiosity-driven exploration to solve the Pyramids environment, where it must press a button to spawn a pyramid, navigate to it, knock it over, and reach the gold brick at the top.
+
+## 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

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": 3000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "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": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "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 +1,90 @@
+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
+      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: 3000000
+    time_horizon: 128
+    summary_freq: 30000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/linux/Pyramids/Pyramids
+  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: true
+environment_parameters: null
+checkpoint_settings:
+  run_id: Pyramids Training
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false