Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -150.01 +/- 86.25
+      value: 35.30 +/- 116.57
       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': 100000
+'learning_rate': 0.01
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1698276535.0d4ecdd00153.9541.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d8f31e9eabf8a1f2f2759d69274acbf648bfea0c7bcbbf8cba34451ebe02852
+size 143639

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
+oid sha256:2bedd865d6166ad4719f5098602113631d2d48470faf488a6a4660ff9ba06c81
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -150.0073264264918, "std_reward": 86.24658858734165, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-25T23:20:49.960843"}
+{"env_id": "LunarLander-v2", "mean_reward": 35.30284779450788, "std_reward": 116.56903622563257, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-25T23:31:44.456407"}