Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 15.40 +/- 13.58
+      value: 18.40 +/- 13.04
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 12000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.98, "lr": 0.0003, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 64, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 0.0003, "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:c7057c27a5e6c1f6511a15761672f49ee301403a51820b6971198351736ff346
+oid sha256:cc82db579cc7c326bcda63282bfe4d42f5742ffb9b6ffdf20ba2c62c96a6a4bb
 size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 15.4, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-19T04:24:49.134307"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 18.4, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-22T07:18:23.716687"}