Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -162.01 +/- 98.96
+      value: 44.92 +/- 18.72
       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': 500000
 'learning_rate': 0.00025
 'num_envs': 8
 'num_steps': 128

logs/events.out.tfevents.1689849408.94dbf6c03cb8.13632.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:192f49b3923b22555ce1f66f51bf72a541c1afe7c7cebbb9b5a6fad7e8a59061
+size 446143

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ebb1f5846fff94bec792a4ca38eae78d6f774162935301b49235162e047a299
+oid sha256:b6830dfa79ac34c5d20fa19592f6f5bab692714c19739e18edad53e466df98a5
 size 40785

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -162.00533440119474, "std_reward": 98.96408562709833, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-20T10:35:32.411868"}
+{"env_id": "LunarLander-v2", "mean_reward": 44.919816257325834, "std_reward": 18.72439179641424, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-20T10:49:40.830311"}