Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 14.70 +/- 10.60
+      value: 11.00 +/- 8.53
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 256, "n_training_episodes": 60000, "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": 256, "n_training_episodes": 100000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.999, "lr": 5e-05, "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:e79328b9aead4157a2b133f6e069a778d1b0292979415953bc22b6e840bc07ef
-size 1592763
+oid sha256:61a59fdaae2d83556c3fd8141074ef7d56a1a9c507634c46390d101aeb3686c4
+size 541575

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 14.7, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-08T01:53:38.866064"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 11.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-08T18:11:29.636822"}