Upload folder using huggingface_hub

README.md

@@ -6,7 +6,7 @@ tags:
 - custom-implementation
 - deep-rl-class
 model-index:
-- name: Reinforce-Pixelcopter
+- name: Reinforce-PixelCopter
   results:
   - task:
       type: reinforcement-learning
@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 8.90 +/- 8.42
+      value: 14.10 +/- 13.77
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 10000, "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": 128, "n_training_episodes": 80000, "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 sha256:04d78a8a2e3dceac2f683abfd66a5bbbb09dbc640bbb2acc02540733dd4f7262
-size 39732
+oid sha256:0b67a0157291fe572d28c23a8d3d3218ce2c028b2cad76c97f24d0788869cf14
+size 141620

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 8.9, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-07T19:36:17.713045"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 14.1, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-04T15:06:51.902971"}