Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 33.70 +/- 8.21
+      value: 491.20 +/- 26.40
       name: mean_reward
     task:
       type: reinforcement-learning

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 16, "n_training_episodes": 1000, "n_evaluation_episodes": 10, "max_t": 1000, "gamma": 1.0, "lr": 0.01, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}
+{"h_size": 16, "n_training_episodes": 10000, "n_evaluation_episodes": 10, "max_t": 1000, "gamma": 1.0, "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 sha256:2ee85f63874191ef81738a97a7b5f1bf1ff9436c4447816c1494d06815dde1d8
+oid sha256:ddbc98a24c6d1eb26228676b6d445d2cecedd966f04de497e19b773683318c6b
 size 2479

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c85c57e6eb78511a6c52b2f9df45b4277bffe82450e16f659f57fc249069585b
-size 9515
+oid sha256:3bcb441989c4bb5a75f2f7180b5fa16bb6a9c9b47635b3e66040665791335d0f
+size 91960

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 33.7, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-08T21:08:56.986152"}
+{"env_id": "CartPole-v1", "mean_reward": 491.2, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-08T23:55:24.037350"}