Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 84.30 +/- 97.41
+      value: 24.40 +/- 18.22
       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": 35000, "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 sha256:01359945b6ebb9c0da646e23f43844831f9c91ecee4d17cbf2a631785e222153
+oid sha256:5e38a2918afd7640e88e104f92a8a97098548d3930f3587f7c9c19e02e4ff2ea
 size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 84.3, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-17T18:27:29.212254"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 24.4, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-19T00:10:43.195150"}