Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 29.44 +/- 35.97
+      value: -108.25 +/- 14.38
       name: mean_reward
       verified: false
 ---
@@ -37,11 +37,11 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 2000000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 1024
-'anneal_lr': False
+'anneal_lr': True
 'gae': False
 'gamma': 0.9999
 'gae_lambda': 0.98

logs/events.out.tfevents.1712943992.58af08d562c1.35165.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51b456c53265811f44933aeef5d81e2319b541833a04e80f4d6bd0c4eb44059c
+size 1501317

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15cdf2c32f3d1c9ac5340afd4772d544232eb22642ecfd8209afb90adeffcf8f
+oid sha256:762badf8d86dc8ae5ff412913ec7e796c3d423cd0ef74c7e93eb1bdc6c9364c4
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 29.440074385873594, "std_reward": 35.970389244790596, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-12T17:05:11.099458"}
+{"env_id": "LunarLander-v2", "mean_reward": -108.24993373513477, "std_reward": 14.378687399809463, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-12T17:55:45.457338"}