Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -122.69 +/- 82.37
+      value: -61.05 +/- 101.92
       name: mean_reward
       verified: false
 ---
@@ -37,13 +37,13 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 200000
-'learning_rate': 0.0003
+'total_timesteps': 500000
+'learning_rate': 0.0001
 'num_envs': 4
 'num_steps': 512
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
+'gamma': 0.95
 'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4

logs/events.out.tfevents.1689493207.8981986e6198.42200.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40e93a89d538d2d3ce92c3888a480c6b07c325fd36ec1e2eae329979b0951b5a
+size 490663

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a522010ab0180b5b45f18791529c0459fdc7ba416ba3db0f18ef426946ccbfc2
+oid sha256:8345e8738962770f40cffe2c5725fcb424206d75f17a3287ee361a20bd1a25d3
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -122.69359882214378, "std_reward": 82.37465602103556, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-16T07:34:28.556599"}
+{"env_id": "LunarLander-v2", "mean_reward": -61.05257374377165, "std_reward": 101.91741754558755, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-16T07:48:42.044325"}