Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -126.16 +/- 65.77
+      value: -108.10 +/- 91.46
       name: mean_reward
       verified: false
 ---
@@ -37,13 +37,13 @@ model-index:
 'wandb_entity': None
 'capture_video': True
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
-'learning_rate': 0.00025
+'total_timesteps': 250000
+'learning_rate': 0.0001
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
+'gamma': 0.8
 'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4

logs/events.out.tfevents.1725426021.coder-william-william-gpu-dev-01-5fd55f9c84-plnfx.1529381.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4128264ede22313552cc1c0dcb60189692b6d56572a4f4fea25c2a93adf45524
+size 419464

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0bee8379c6900506726ea5a3990eb0003996db65b2f1015b138a8f71be43f52
+oid sha256:4239cef4aac053d458e15c34ea82a3fd000fd0387f0961bcabd9eac4e11def3a
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -126.16086227227284, "std_reward": 65.77039070781815, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-04T12:59:35.846009"}
+{"env_id": "LunarLander-v2", "mean_reward": -108.09963298596685, "std_reward": 91.45784393374818, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-04T13:02:50.048891"}