Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 13.40 +/- 12.46
+      value: 59.10 +/- 36.93
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 20000, "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:e2b6cad63f19ed492d98aa9b302982b6be1dce21cb502eb23512ab73fe9382de
+oid sha256:e2d3ba29c78ed360c0843fd7cbe15a4de51b021da18aa06b559a454e360f7051
 size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 13.4, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-25T14:42:24.231307"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 59.1, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-27T11:28:55.275355"}