Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -199.78 +/- 130.55
+      value: -183.15 +/- 66.83
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 1e-05
+'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.1685093642.2850cb3f29b2.18056.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8859c7a6f04f447b8f02a54bf7d80a8d289aaad7bbc7d66fcba75880c62044a2
+size 115414

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eefce50389ac81019a8c3d559626432f025e6cb2a1f2e326bf421214d23c2a3d
+oid sha256:a108327552bb500e57e82eaae0ae7ab5cad2dd9c012a2b4c88e642d5febe045c
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -199.77985861976214, "std_reward": 130.5450547968825, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T09:30:37.498058"}
+{"env_id": "LunarLander-v2", "mean_reward": -183.15377998821666, "std_reward": 66.83021323082126, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T09:34:42.709385"}