Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -30.44 +/- 48.27
+      value: -115.06 +/- 29.28
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 250000
-'learning_rate': 0.00025
+'learning_rate': 1e-05
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1684423018.irow-pc.65926.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c9776336616e3d5f13e09f1c32ef05819208c4fc1d8a43531259259fdf97aa9
+size 572587

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12ed0921b7b02109ed65fc4ec546fd264e6362e91035045cf295fe896d12a2d8
+oid sha256:0880b3fff8754fdc27aa13e5ce7578237f78b0a02a618452c2b0b35f816ce812
 size 42817

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -30.443244319799454, "std_reward": 48.265887924244666, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-18T09:15:14.467094"}
+{"env_id": "LunarLander-v2", "mean_reward": -115.05908674477487, "std_reward": 29.280940153403936, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-18T09:18:51.159521"}