Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -248.98 +/- 123.05
+      value: 20.19 +/- 120.39
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 20000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1692158090.c32692033c6b.4395.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2117c7ebd9af7d9742e0831275145daa97ba25eed26e85d973278ab3efc0ae1
+size 1296804

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0f946736a9234bd22e172f86fa80497bc2a900848f0c6ebb7945afeeca2444c
+oid sha256:16c14154a3239d4afb840cfc54bd5b1191d7ba55775f805d70c2dc0318a3d85c
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -248.98023050458224, "std_reward": 123.04506393590731, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-16T03:53:40.711786"}
+{"env_id": "LunarLander-v2", "mean_reward": 20.187857943734894, "std_reward": 120.38986526044974, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-16T04:19:41.345449"}