Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -5.00 +/- 0.00
+      value: 8.00 +/- 4.88
       name: mean_reward
     task:
       type: reinforcement-learning

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 128, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 0.01, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 128, "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:a91ad96be44345378771fc4340df4feb6d59234937dcc9dc2ea2648387dda2bf
+oid sha256:55db36eca4b7d38a4b9cfdec07daa5d2d84d3bbed0cd680e59bcc25c4bcc3ece
 size 7135

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c23b99089c22e3d7d42c90bd84c0329f35c82686700f9b9c027f053dd4a2d0d
-size 2095
+oid sha256:3d39935af2d05f8dffe2336fc028b3ce043701713a8c30e7bdf8024822baa797
+size 6135

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -5.0, "n_evaluation_episodes": 10, "eval_datetime": "2022-06-29T23:54:21.484902"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 8.0, "n_evaluation_episodes": 10, "eval_datetime": "2022-06-30T00:11:50.584550"}