Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -143.27 +/- 59.25
+      value: -199.78 +/- 130.55
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.00025
+'learning_rate': 1e-05
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1685093396.2850cb3f29b2.16974.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ebb568d77c0724c140f4d0d70b2dd2cb2c6ca45e6f8cf086e6253029a41d3b
+size 114913

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f5fb2118f91271b2b7c766e15246af5126119020a3ba8448fd1cfd461405f78
+oid sha256:eefce50389ac81019a8c3d559626432f025e6cb2a1f2e326bf421214d23c2a3d
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -143.26696784927753, "std_reward": 59.24760826876614, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T09:28:17.908103"}
+{"env_id": "LunarLander-v2", "mean_reward": -199.77985861976214, "std_reward": 130.5450547968825, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T09:30:37.498058"}