Push Reinforce agent to the Hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: -2.70 +/- 0.46
+      value: 13.90 +/- 14.43
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 1024, "n_training_episodes": 5000, "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 sha256:1bc9d0246b0a1a8afbba7bf5349248dd67b053efd45de518f0a64637c50f290a
-size 14052933
+oid sha256:6c4aa1964513531c80dce40da429d6262e14172fa8c4dc987d9536ace3f30102
+size 4691

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27e7b52c53ed8e60c16f502ca615a75914a630e07b2174809fdcf8cb397a2a7a
-size 3488
+oid sha256:9440ef1c52050007c91b0e41ea3f817d24470148ceaba39b812507068836aee8
+size 10436

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -2.7, "n_evaluation_episodes": 10, "eval_datetime": "2022-12-08T20:40:16.872567"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 13.9, "n_evaluation_episodes": 10, "eval_datetime": "2022-12-08T22:55:05.920566"}