Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -146.57 +/- 67.28
+      value: -3.74 +/- 103.48
       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': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
+'gamma': 0.999
 'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4

logs/events.out.tfevents.1728674641.712e2f2e4997.8941.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c96a2f23bda32d7fd8780a452939b8280615c5a2d4cffe8e9920c66e1d53ef6
+size 1304156

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b51141f29a5fd60d9f7a96a70a1e185897fcb1c4838b12131a7276001db13c08
+oid sha256:3f3be42c0b11a52a497da23ce710345902a7b5812c5ed22a30bf9d3a9f699baf
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -146.57247364388866, "std_reward": 67.27856848926791, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-11T19:17:33.190936"}
+{"env_id": "LunarLander-v2", "mean_reward": -3.737083207498961, "std_reward": 103.47904261932031, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-11T19:56:19.166037"}