Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 16.80 +/- 15.76
+      value: -2.80 +/- 0.40
       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": 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}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e58269d829be5f073eb4cbd07db1a726afbb39877dde6863a889336d5fac5f91
-size 21767
+oid sha256:33bb1e4e50005ac9b427923f0bc1d2aded643d38da69088e7318a63f5317125c
+size 73735

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 16.8, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-28T22:06:39.072715"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -2.8, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-28T22:33:39.228854"}