Upload . with huggingface_hub

README.md

@@ -0,0 +1,27 @@
+---
+tags:
+- Pixelcopter-PLE-v0
+- reinforce
+- reinforcement-learning
+- custom-implementation
+- deep-rl-class
+model-index:
+- name: Reinforce_Pixelcopter-PLE-v0_v2
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Pixelcopter-PLE-v0
+      type: Pixelcopter-PLE-v0
+    metrics:
+    - type: mean_reward
+      value: 63.90 +/- 43.52
+      name: mean_reward
+      verified: false
+---
+
+  # **Reinforce** Agent playing **Pixelcopter-PLE-v0**
+  This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
+  To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
+  

hyperparameters.json

@@ -0,0 +1 @@
+{"n_hidden1": 64, "n_hidden2": 128, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.992, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "n_states": 7, "n_actions": 2, "print_every": 500}

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfceb94c6a24481523bf972b91eae7cd4e1061ad92918bc1f40bb0cccb71ed17
+size 38983

results.json

@@ -0,0 +1 @@
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 63.9, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T13:27:19.922268"}