Upload folder using huggingface_hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- CartPole-v1
+- Pixelcopter-PLE-v0
 - reinforce
 - reinforcement-learning
 - custom-implementation
@@ -12,16 +12,16 @@ model-index:
       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: 500.00 +/- 0.00
+      value: 24.00 +/- 20.29
       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 +1 @@
-{"h_size": 16, "n_training_episodes": 1000, "n_evaluation_episodes": 10, "max_t": 1000, "gamma": 1.0, "lr": 0.01, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}
+{"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}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:add68111eb6205c3f94e55b517fc5d73685218985b0d9a2d241569610430ac93
-size 3264
+oid sha256:1e70dc33e3d02ac489e9f7554da194eedf8847b7fda428012c0688e21ac0d383
+size 39732

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 500.0, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-31T03:08:12.297102"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 24.0, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-01T03:50:59.932258"}