Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 38.30 +/- 26.74
+      value: 43.50 +/- 53.42
       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": 64, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.98, "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:b14e99b84dea4efda8f34efeaac02c8f0959c5c6a50ee1b5f7570b4f6a2aeb5f
-size 38983
+oid sha256:538bb4daed607ec0b8abbda07b3f075b46826f88b2a5165a4da055f5a05e66ad
+size 39431

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 38.3, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-12T07:03:41.706772"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 43.5, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-12T23:34:08.275051"}