Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 21.80 +/- 19.29
+      value: 96.00 +/- 61.88
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "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}
+{"h_size": 128, "n_training_episodes": 100000, "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:ead13839ce03424b995ce6fd18d2038b2bdb7110534c54a537fd471a5701f8ec
-size 38983
+oid sha256:1edaa063db895d6af92bbaeff1cc5ac0d8495bdd54928c71eba2f2f834395e95
+size 140871

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 21.8, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-15T23:56:44.425576"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 96.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-16T12:28:41.492410"}