Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 10.20 +/- 6.57
+      value: 13.10 +/- 18.92
       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": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 64, "n_training_episodes": 100000, "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 sha256:9b392cd659b8d910c99adf2a55956e6c5461d6cc12f7f25cc8041423cc60e18e
-size 4703
+oid sha256:6fac57e66f7404da1ee7ec18e6cadf1e1cc0b78175159d1776796609065c448d
+size 4639

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7173763b6efe9491d9100c45d303d5118a62b361b4c8f898822a1babd75ebca8
-size 8077
+oid sha256:839db1867d703b9e475625a5fc41d9023a50bb82b2de4e898f99ae88cb819110
+size 9494

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 10.2, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-02T12:45:29.720377"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 13.1, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-03T09:29:11.676822"}