Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 51.50 +/- 20.49
+      value: 359.42 +/- 89.49
       name: mean_reward
     task:
       type: reinforcement-learning

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 32, "n_training_episodes": 5000, "n_evaluation_episodes": 20, "max_t": 1000, "gamma": 0.99, "lr": 0.0001, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}
+{"h_size": 32, "n_training_episodes": 5000, "n_evaluation_episodes": 1000, "max_t": 1000, "gamma": 0.99, "lr": 0.001, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9bec14de42b9cf5aee1f746dbf8e794f2f9d87d2c1c2fc11db016a02eb18af0
+oid sha256:53e61ef5a6e2395c529b423c6d85465c23584eff74538c9a7d3a190ff22f1408
 size 2975

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42f98e7feed2b679be3ae6b7cd744d16d6e46de9c1c25f9e05f13013328814fe
-size 10894
+oid sha256:469d86a62ea0d353611171205835866612656da4980a4652cc3f2863045dd04b
+size 47333

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 51.5, "n_evaluation_episodes": 20, "eval_datetime": "2022-07-11T17:10:29.239970"}
+{"env_id": "CartPole-v1", "mean_reward": 359.416, "n_evaluation_episodes": 1000, "eval_datetime": "2022-07-11T17:36:13.222128"}