Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -129.45 +/- 74.51
+      value: -221.14 +/- 170.03
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.00025
+'learning_rate': 0.0001
 'num_envs': 4
 'num_steps': 256
 'anneal_lr': True
@@ -46,7 +46,7 @@ model-index:
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 8
-'update_epochs': 4
+'update_epochs': 6
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True

logs/events.out.tfevents.1718025017.887b5cfc0142.10621.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4648c67b5e4b9253151796deb42b43cee5a021309cee55944046ef531c0a677d
+size 88092

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9e6761d04b9104eda1781c46bc16172cc73d4a36fa94047d3047ff6860b20ee
+oid sha256:7c03d26812b5698b0e80f322107916a141fd17c54e3616b37ed86dfafba499c2
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -129.4519122783003, "std_reward": 74.51302299483893, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T13:09:23.976436"}
+{"env_id": "LunarLander-v2", "mean_reward": -221.13670925092933, "std_reward": 170.03142679682054, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T13:11:05.131029"}