Upload folder using huggingface_hub

README.md

@@ -6,7 +6,7 @@ tags:
 - custom-implementation
 - deep-rl-class
 model-index:
-- name: Reinforce-pixelcopterv1
+- name: Reinforce-PixelCopterV1
   results:
   - task:
       type: reinforcement-learning
@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 13.80 +/- 15.29
+      value: 15.00 +/- 14.35
       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": 64, "n_training_episodes": 30000, "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 sha256:19097ca6a05d7717af372c79553af67fbb5a6f7fc5b7b2c7310af84c08403eaa
+oid sha256:5e53246827064137b030dbfdb9983c964014c59af95a5000d705528743a8c043
 size 39732

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 13.8, "n_evaluation_episodes": 10, "eval_datetime": "2024-11-12T16:51:11.923491"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 15.0, "n_evaluation_episodes": 10, "eval_datetime": "2024-11-13T19:14:47.302380"}