Upload folder using huggingface_hub

README.md

@@ -6,7 +6,7 @@ tags:
 - custom-implementation
 - deep-rl-class
 model-index:
-- name: Reinforce-PoliCopter
+- name: Reinforce-policopter
   results:
   - task:
       type: reinforcement-learning
@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 19.90 +/- 26.20
+      value: 22.30 +/- 18.57
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 45000, "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": 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}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3526f2027734f39f0f1a976abc7d82bdc35c42fbe632019968bc5451991ee5a
+oid sha256:ce0ffcfc215c6a23b7d7c051e5fd287ec754e8d2ff6047dd0a22ed57c5cc0dea
 size 40125

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 19.9, "n_evaluation_episodes": 10, "eval_datetime": "2025-09-12T16:04:19.149065"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 22.3, "n_evaluation_episodes": 10, "eval_datetime": "2025-09-12T16:37:46.459710"}