Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -2.70 +/- 0.46
+      value: -5.00 +/- 0.00
       name: mean_reward
     task:
       type: reinforcement-learning

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 0.001, "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": 0.01, "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:d192233f1feb8874d02ff43f4cf8f20c78c25ce4177ca79db35e365c506eb01e
-size 3295
+oid sha256:a91ad96be44345378771fc4340df4feb6d59234937dcc9dc2ea2648387dda2bf
+size 7135

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b7f1112d3e3675ce58987a190045d5ac24742180b0a185d1bc38b0d6ee847b2
-size 2988
+oid sha256:4c23b99089c22e3d7d42c90bd84c0329f35c82686700f9b9c027f053dd4a2d0d
+size 2095

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -2.7, "n_evaluation_episodes": 10, "eval_datetime": "2022-06-29T23:39:12.048437"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -5.0, "n_evaluation_episodes": 10, "eval_datetime": "2022-06-29T23:54:21.484902"}