Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -148.88 +/- 83.12
+      value: -1.41 +/- 58.92
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1685524358.alex-pc.9036.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a07d2fc2b7fb90892a0c2528f195cd6b7cf2d9d85c09ba4ebd935156896665f
+size 672375

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39cb515eaeed9638a752315dd231fbedd4b297b0656a512ec1cbe6076cb19b25
+oid sha256:2aa2ea8d3383d2f1df22b0330bd7ed0eecb271ca3023819a07ae6c8c6eeff823
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -148.88253431196864, "std_reward": 83.12333555514344, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-31T12:12:11.577465"}
+{"env_id": "LunarLander-v2", "mean_reward": -1.414669166410998, "std_reward": 58.9214403568734, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-31T12:43:18.432637"}