Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -180.75 +/- 118.13
+      value: -32.16 +/- 82.95
       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': 2000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1719396138.cf8e4b12a04a.2957.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ea3be03d84dbf6bd44d46dafb930da2978ff3e59a700c9da2d9ed7081b1f8ab
+size 2687149

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
+oid sha256:bb63fef1f58bd511a7c93a1d585c94225a8aae97012f944641151d165c791795
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -180.74961892666406, "std_reward": 118.1311110666655, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-26T10:01:32.642669"}
+{"env_id": "LunarLander-v2", "mean_reward": -32.16469695084163, "std_reward": 82.94773967647075, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-26T10:45:57.970500"}