Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 17.00 +/- 20.34
+      value: 21.80 +/- 16.76
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 96, "n_training_episodes": 10000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 1, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 96, "n_training_episodes": 10000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.95, "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 sha256:388d67c20ecf3c87813f4beed71be308336943f99f99d8a7c97506ddcfbee7d4
+oid sha256:21746a866cbb067a92b4b82378c15ac34b19c2ab08c459531d308a4d181d14f2
 size 5971

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 17.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-15T09:08:24.995863"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 21.8, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-15T10:07:51.803754"}