Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 185.00 +/- 74.19
+      value: 28.90 +/- 14.52
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'CartPole-v1'
 'total_timesteps': 50000
-'learning_rate': 0.00025
+'learning_rate': 3e-05
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
@@ -48,7 +48,7 @@ model-index:
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.2
+'clip_coef': 0.05
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5

logs/events.out.tfevents.1685094295.2850cb3f29b2.21241.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7731f673fc6f72c643b98a0fa039016d7f9b97bb065f056cc303b691594d5c9e
+size 248654

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b9ca349a915ce403f54d2a621d55d831b6eba9513b8b32511333fc1910bc53c
+oid sha256:e577ddec21819afb3661a47de34f9a2b58dd27c43712220fe4d5194e46d5dc98
 size 40037

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 185.0, "std_reward": 74.1862520956545, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T09:42:49.858228"}
+{"env_id": "CartPole-v1", "mean_reward": 28.9, "std_reward": 14.515164484083535, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T09:45:27.305171"}