Pyramid pushed

Pyramids-499902.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2b0ee5743deaccdfbfa3f2761d1e6909ab250d8708a74c8ff3aa1695a9f613a
+size 1418184

Pyramids-499902.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbd069481d9134a53c39992ebca92696bd077c87f66e8299e6f536b3ea7843fc
+size 8650990

Pyramids-500030.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2b0ee5743deaccdfbfa3f2761d1e6909ab250d8708a74c8ff3aa1695a9f613a
+size 1418184

Pyramids-500030.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3024dbffa86b6752cf9b46de0b4656de852b1a01e7a9054fb99e9e58ceaf3b1e
+size 8650990

README.md

@@ -0,0 +1,29 @@
+---
+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://github.com/huggingface/ml-agents#get-started
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+
+
+  ### Resume the training
+  ```
+  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. Go to https://huggingface.co/spaces/unity/ML-Agents-Pyramids
+  2. Step 1: Find your model_id: rlucasz93/ppo-Pyramid
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3024dbffa86b6752cf9b46de0b4656de852b1a01e7a9054fb99e9e58ceaf3b1e
+size 8650990

config.json

@@ -0,0 +1 @@
+{"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, "learning_rate_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple"}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"hidden_units": 64, "num_layers": 3}, "learning_rate": 0.0001}}, "keep_checkpoints": 5, "max_steps": 500000, "time_horizon": 128, "summary_freq": 30000}}}

configuration.yaml

@@ -0,0 +1,32 @@
+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
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 2
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+      rnd:
+        gamma: 0.99
+        strength: 0.01
+        network_settings:
+          hidden_units: 64
+          num_layers: 3
+        learning_rate: 0.0001
+    keep_checkpoints: 5
+    max_steps: 500000
+    time_horizon: 128
+    summary_freq: 30000

events.out.tfevents.1681249406.701fd5495228.1858.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec3d7a531d5d01246a4ef31929b845aa6ca249fa05ce9c98b402490c6e6ae990
+size 138399