Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -88.16 +/- 70.74
+      value: 107.73 +/- 31.19
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1677857473.0944e74d2880.3610.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4080fc85640dbc19a8bb0e0fd94fa9a7a5aca32d95b4298cc770392493881e0
+size 659813

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcd2d09ce108a051e2e384d5e01bda71dd42ff9b117e243d3d4f61911fd43a9d
+oid sha256:a9f46f0c7b70f362e72eed22c3293e3d84fecfb7f3a67337d95096ecff1763a0
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -88.1594933443973, "std_reward": 70.742268220681, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-03T15:30:20.908755"}
+{"env_id": "LunarLander-v2", "mean_reward": 107.73063223115396, "std_reward": 31.18707606078402, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-03T15:45:20.494065"}