Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 34.04 +/- 57.20
+      value: 9.12 +/- 126.17
       name: mean_reward
       verified: false
 ---
@@ -37,13 +37,13 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 500000
-'learning_rate': 0.0002
+'total_timesteps': 300000
+'learning_rate': 0.001
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.995
+'gamma': 0.98
 'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4

logs/events.out.tfevents.1680163354.9015aca90cf1.14731.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcec87c0785c1b6c1b0df46d8c42aed4320373148f5263583b59e982764200ee
+size 301680

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5f2ece289c1b067918299d10a5b1d242a017b793dd36c756248751da9955b87
+oid sha256:91aa0298e8b62bffcf6368f449e7adbd4054ba1b8b5eb304eee9e347b9fd2a91
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 34.03965676341449, "std_reward": 57.19536895009466, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-30T07:43:11.098509"}
+{"env_id": "LunarLander-v2", "mean_reward": 9.116140402791174, "std_reward": 126.16834083585978, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-30T08:11:53.806279"}