Upload . with huggingface_hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -5.00 +/- 0.00
+      value: 39.60 +/- 26.93
       name: mean_reward
     task:
       type: reinforcement-learning

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 256, "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": 0.99, "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:c27c7478d66314f4e69794bb869b47f73bbc60818dbfadc385a9d3c6d880f876
-size 541255
+oid sha256:7329fcf3e7cee8e7c9e3a7f62e8ceafe57eb9a0d582fafb0e0b53a9474c84bf4
+size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -5.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-14T16:01:27.808193"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 39.6, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-15T11:30:26.236888"}