Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -137.79 +/- 88.05
+      value: -1555.86 +/- 2779.71
       name: mean_reward
       verified: false
 ---
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
-'learning_rate': 0.00025
+'total_timesteps': 1000000
+'learning_rate': 0.025
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1736801643.ebc41fb37504.4890.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8da0d5379521aff4525a931a00934e9c296760236c9503dd5a989078f2d22e91
+size 2016006

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:339f09e8b06f686b9c10d26099e14e7a7303e9b6ecce9f9f6a67b3d5b02b6551
+oid sha256:c331d1fb35daeb3fd34135eef6cc515240a6edf3e0c140b0890f3ab34791eb4d
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -137.79424810405246, "std_reward": 88.0517634571268, "n_evaluation_episodes": 10, "eval_datetime": "2025-01-13T20:49:51.060991"}
+{"env_id": "LunarLander-v2", "mean_reward": -1555.8568090329893, "std_reward": 2779.706929395287, "n_evaluation_episodes": 10, "eval_datetime": "2025-01-13T21:08:55.948459"}