Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -264.32 +/- 128.26
+      value: -122.54 +/- 46.55
       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': 1000000
 'learning_rate': 1.5e-05
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1679401604.7b0e271d7d17.19945.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70fab7049a4fbd340176c9bca1ad9dfefa776e51afdd677018cc46e6bf684c44
+size 2072628

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6914b2dc697158cfda58dbb9d6e64da35d8f6bc152301dbee130d7fb443ac37c
+oid sha256:1ab90fd79386fee05c1a73e33cacb6fe354813e20fb2dc9709217b6f57c00714
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -264.32433893266153, "std_reward": 128.25850053142534, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-21T12:24:16.751548"}
+{"env_id": "LunarLander-v2", "mean_reward": -122.54416146040305, "std_reward": 46.54687351532792, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-21T12:39:21.383974"}