Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 18.10 +/- 13.60
+      value: 84.10 +/- 64.26
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.999, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 64, "n_training_episodes": 100000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.989, "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 sha256:0898645bd57a40b68b699c29b5101fdbedfc148b9a9e5f758b38e342e82efde8
+oid sha256:c37efb02f520fdda6b19a98de94af75afe18d3427deb970f5b9552695f0f2b6f
 size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 18.1, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-30T19:28:19.181208"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 84.1, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-31T16:19:05.081495"}