Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -156.60 +/- 84.64
+      value: 109.78 +/- 128.11
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 3000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1680285918.63f38e4bb856.5724.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ef0b61d0f1e2384ed114669d2fb7066a68f68b27e419d85b731fceb4a2b0260
+size 4129304

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0762c60b8952f57601a85c2d5d3d6f6e862f4cc07ba530b06e3bd7b2d806a2a3
+oid sha256:64bc71d3d42595cafa11c4a13017166e2ee100bc64b3081f38c642fee3ae7e44
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -156.59879599999945, "std_reward": 84.63732176054754, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-31T18:02:36.975985"}
+{"env_id": "LunarLander-v2", "mean_reward": 109.78472305039539, "std_reward": 128.10545107698556, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-31T19:06:10.093977"}