Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -75.41 +/- 84.31
+      value: 150.26 +/- 122.99
       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': 5000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1684000674.c6e3bac58bc0.3469.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a513c2dc642d58d2496098f55c37a0a7853280f6e53ca9793fffb97106f22c97
+size 7125377

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40b5ee98fe5b77f599f75eced20a5c68d36ddeea5a4e95056c913a979871babc
+oid sha256:fdec2167c299a241a736647739462d1aca263ac68ca9487c752531f08f7c4387
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -75.40532175383694, "std_reward": 84.31239048651376, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-13T17:46:15.235422"}
+{"env_id": "LunarLander-v2", "mean_reward": 150.2595110262988, "std_reward": 122.99300178273775, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-13T20:13:32.681582"}