Upload 5 files

README.md

@@ -1,27 +1,27 @@
 ---
 tags:
-- CartPole-v1
+- Pixelcopter-PLE-v0
 - reinforce
 - reinforcement-learning
 - custom-implementation
 - deep-rl-class
 model-index:
-- name: Reinforce-Pixelcopter-PLE-v0
+- name: Reinforce_pixelcopter
   results:
   - task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: CartPole-v1
-      type: CartPole-v1
+      name: Pixelcopter-PLE-v0
+      type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 22.20 +/- 6.32
+      value: 21.80 +/- 16.40
       name: mean_reward
       verified: false
 ---
 
-  # **Reinforce** Agent playing **CartPole-v1**
-  This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
+  # **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

@@ -1,9 +1 @@
-{'h_size': 64,
- 'n_training_episodes': 50000,
- 'n_evaluation_episodes': 10,
- 'max_t': 10000,
- 'gamma': 0.99,
- 'lr': 0.0001,
- 'env_id': 'Pixelcopter-PLE-v0',
- 'state_space': 7,
- 'action_space': 2}
+{"h_size": 64, "n_training_episodes": 20000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c651fd496de85aef6ed8e4a03d361b4d326a6e8131dbfc2742cc7046ac4f736
-size 38215
+oid sha256:7099c687d10bff7c8e5c311af6b1debc06f884cfa0d5ac7a393dadc9f33c8b6f
+size 38983

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 22.2, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-09T17:21:15.457691"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 21.8, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-08T12:15:14.893463"}