Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -215.86 +/- 102.31
+      value: 133.96 +/- 135.43
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 25000
+'total_timesteps': 2000000
 'learning_rate': 0.0003
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1689453704.bf97217af71f.16764.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04590a0e3b97ef0f0254865932ef9cd38ae5b42a8af17edcaea091208fa87c21
+size 2721626

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab48172f65641422be21250476884225eca544386aced8832d7b227255ffa402
+oid sha256:010fa71b35dec8488a288c44d95d07d584ffaacb60d3281540447684b173481c
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -215.86234612452944, "std_reward": 102.31260803695999, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-15T20:39:50.876578"}
+{"env_id": "LunarLander-v2", "mean_reward": 133.95622126361656, "std_reward": 135.43248799912354, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-15T21:23:24.856442"}