Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -64.64 +/- 92.05
+      value: 75.61 +/- 101.50
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000000
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1677165655.0d28c766a9e5.18594.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7e6d4a5ea27c485f35485bc5476b0cd52b7576af2f02ab2454d9967ff18fd5e
+size 659826

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebb378896b2cb4c43e971f50d7380e681cb99523b73cd341f85c99706c03d9df
+oid sha256:a9f46f0c7b70f362e72eed22c3293e3d84fecfb7f3a67337d95096ecff1763a0
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -64.6367906001573, "std_reward": 92.05366408610439, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-23T15:17:18.861700"}
+{"env_id": "LunarLander-v2", "mean_reward": 75.60835708601816, "std_reward": 101.496756997856, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-23T15:36:26.517797"}