Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -164.89 +/- 105.61
+      value: -148.88 +/- 83.12
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 5000
+'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1685524297.alex-pc.8881.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c48a21f21f9d4653576be76bf28ae3119682f7aa8fc763804dfd709a2b880d4c
+size 110591

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d039f132914d087d7ca0c814b9d0de3992702a7c654ee15418c26919e7b96b4
+oid sha256:39cb515eaeed9638a752315dd231fbedd4b297b0656a512ec1cbe6076cb19b25
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -164.88952286139113, "std_reward": 105.61030070415077, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-31T12:10:23.076887"}
+{"env_id": "LunarLander-v2", "mean_reward": -148.88253431196864, "std_reward": 83.12333555514344, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-31T12:12:11.577465"}