Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -103.86 +/- 24.51
+      value: -91.96 +/- 53.74
       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': 200000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1718524313.df899c0c4fcb.6430.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:742cb96146698df2e94a2c6d5a98d94311406502882d9b23cb21471da17253fa
+size 381008

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b51141f29a5fd60d9f7a96a70a1e185897fcb1c4838b12131a7276001db13c08
+oid sha256:d9a2995457e0c630f5e430cac95c0f621497de16ba9ad0997bec66b0c61e7c33
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -103.85663680758528, "std_reward": 24.505784468616223, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-16T07:41:14.666580"}
+{"env_id": "LunarLander-v2", "mean_reward": -91.95531894063646, "std_reward": 53.7447919862502, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-16T07:54:41.390642"}