Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -189.52 +/- 89.08
+      value: -63.82 +/- 61.20
       name: mean_reward
       verified: false
 ---
@@ -37,13 +37,13 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 200000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.9
+'gamma': 0.98
 'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4

logs/events.out.tfevents.1698072965.527fe3665085.26734.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b24e7892dccb3a60faffb64d0e3040f7901162fa9dc26315e9d2ae590cfb7a16
+size 335389

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4b2597fbfa39796395fcd740a004c216c108e429a79d8560df69ee364f27f8b
+oid sha256:e8efa7dc03824403a87d331a1629d4c059898e96ef654d2868f2c42a94632f69
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -189.5197540517459, "std_reward": 89.077803164192, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-23T14:53:47.919341"}
+{"env_id": "LunarLander-v2", "mean_reward": -63.81700733366519, "std_reward": 61.19662367355915, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-23T14:59:52.442044"}