Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -131.98 +/- 51.13
+      value: 168.39 +/- 108.87
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 5000
+'total_timesteps': 5000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1680952899.7ed20663a70a.19302.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:132d092f1c3f2db09217c94540c07130b697fc3f5bc294b24c3161847dd92e3f
+size 7110674

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:accd3b666744db8c630f99d3e344320c08df757c8a7fd83da700199a3b81e6a8
+oid sha256:dfb5e7d12aa933f36f36e59e7667a9312a3c085170349a9b36076e91dfe47f4b
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -131.97517965619318, "std_reward": 51.13272322351979, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-08T11:16:50.588246"}
+{"env_id": "LunarLander-v2", "mean_reward": 168.38919401085647, "std_reward": 108.87236696018307, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-08T13:04:14.059342"}