Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 16.10 +/- 20.65
+      value: 27.00 +/- 21.74
       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": 40000, "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:a637f27d7c8e423bf74c4cbbd575dcec759cdcdf23563415ba841b450363b012
+oid sha256:5d8f1e768f1a8843593f460171c4c9422feffb59d2114429025d6d0f2c4e8a2e
 size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 16.1, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-12T10:30:22.028307"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 27.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-12T16:30:41.228269"}