Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -110.24 +/- 49.24
+      value: -36.39 +/- 28.79
       name: mean_reward
       verified: false
 ---
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
-'learning_rate': 0.003
+'total_timesteps': 500000
+'learning_rate': 0.0003
 'num_envs': 16
 'num_steps': 1024
 'anneal_lr': True

logs/events.out.tfevents.1684284694.6581931b20e0.31110.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0fdbdc325a1a30533e57a573c8f989d9bd18c7945336193d1ab872dfbcd828a
+size 407960

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b5dc6a914b3297b658aaedefe67ffcf4c709750f846b07c4a0a60bac67d7ed7
+oid sha256:292c0e5ee58a7540329d1c1ef08ce0abe25ac104562ce55a153840de1dd836cf
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -110.24029883756855, "std_reward": 49.24128430384795, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-17T00:49:42.518598"}
+{"env_id": "LunarLander-v2", "mean_reward": -36.388281806671955, "std_reward": 28.786278803200254, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-17T00:56:48.968971"}