Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 97.92 +/- 98.65
+      value: 281.02 +/- 18.62
       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': 3276800
 'learning_rate': 0.00025
 'num_envs': 64
 'num_steps': 512

logs/events.out.tfevents.1699946281.9b4eccf047ee.2071.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8b84528c52c8c0756b64a31195e02da5a968d9a84c5d033d47f4eb4c92ec1c4
+size 1263629

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58bb932fed2741352988345b2ea1bce736d45535fd9229284716d3a48558539d
+oid sha256:561f92ef252e9b8a1c9af3871ab3234cd8c15c3bae99e26e8c4fe9e98125472f
 size 80402

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 97.92185554587627, "std_reward": 98.6527904973274, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-13T12:55:40.553439"}
+{"env_id": "LunarLander-v2", "mean_reward": 281.02086423229116, "std_reward": 18.61652623235659, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-14T08:30:30.074237"}