Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 216.20 +/- 82.35
+      value: 456.90 +/- 91.48
       name: mean_reward
     task:
       type: reinforcement-learning

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 32, "n_training_episodes": 3000, "n_evaluation_episodes": 10, "max_t": 1500, "gamma": 0.995, "lr": 0.001, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}
+{"h_size": 32, "n_training_episodes": 3000, "n_evaluation_episodes": 10, "max_t": 2000, "gamma": 0.999, "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 sha256:58af3ab6dbe7481151768bf2ffa6ab9274191869b9127615c09ddf5ae6c909e6
+oid sha256:a8e10edd1fb3c2e9f6dfc0f0dd31d19ddfadfa1986786baadfc22702c31f5e13
 size 8215

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a07dd95b713f8c316eacdfd452285d17293a15e1d16fc8f503283a97b7296e3
-size 24014
+oid sha256:e94739b3d47944cf96ec736b83fd4e8468fdcc8b14887cab524a62d7803cdf4c
+size 44440

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 216.2, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-31T12:30:57.897923"}
+{"env_id": "CartPole-v1", "mean_reward": 456.9, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-31T12:59:33.422587"}