Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -58.71 +/- 96.36
+      value: -13.55 +/- 101.24
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 500000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1689263190.7273d16be8f4.15984.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:077ef106eb1aaceb1df2e0baf652ddf0639dd027986244cc577058a372a70421
+size 1290991

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95d2db815a33646e84e478628a4da4f156c95480a7b55276eebdc219ec4fcd18
+oid sha256:2d7ca9d094a695f309c8f59fe5c7ada825cb4baebdecf651ad75721ad0e1b6e8
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -58.70511020536851, "std_reward": 96.3622441144504, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-13T15:45:40.728073"}
+{"env_id": "LunarLander-v2", "mean_reward": -13.551448837001761, "std_reward": 101.23632489083278, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-13T16:15:14.900166"}