Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -94.87 +/- 85.63
+      value: -175.49 +/- 117.96
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 10000
 'learning_rate': 0.0001
 'num_envs': 4
 'num_steps': 1024

logs/events.out.tfevents.1691959493.bcadd1928d08.11528.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65ec8995b95ac889d013fa2f4e18cdcfe5b0cffda12685a46aaac50f608de1f5
+size 11984

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7060a96771d52696a93e474005107866a7cd2c6bb3d3fcce9cc7769ef908d41f
+oid sha256:3cbab9c63d0d05e44a36044bc75f5bf8f6d43380e888066e4128f66e25a752b0
 size 4285797

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -94.86771239036132, "std_reward": 85.62780819319504, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T20:44:20.187452"}
+{"env_id": "LunarLander-v2", "mean_reward": -175.48532932864288, "std_reward": 117.96010241402351, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T20:45:07.065148"}