Upload folder using huggingface_hub

README.md

@@ -16,9 +16,9 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 10.50 +/- 21.67
+      value: 58.20 +/- 54.60
       name: mean_reward
       verified: false
 ---
 # Reinforce Agent playing Pixelcopter-PLE-v0
-Mean reward: 10.50 +/- 21.67
+Mean reward: 58.20 +/- 54.60

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 128, "n_training_episodes": 5000, "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": 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:cc04acbbafc67a1de5d9e0948eab4c0faff320cb512b28db92f230f41e1e38c5
+oid sha256:e48ced777307666c5619a0fa0a393ea79073638a06e527cd6a661b1e63e40ae9
 size 74548

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 10.5, "n_evaluation_episodes": 10, "eval_datetime": "2026-01-01T07:28:40.961162"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 58.2, "n_evaluation_episodes": 10, "eval_datetime": "2026-01-01T09:30:12.287332"}