Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -219.36 +/- 134.00
+      value: -192.95 +/- 90.63
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 5000
+'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1721830197.9b825996513b.13232.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b9e54865f714916efc2c80d1a4d437a2c804c452ec13b74d54410d39796ea66
+size 110091

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ac1132b34cd37aa87733061e6a98553092d12cd0f7def24c3ac087df8388a48
+oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -219.3568708613489, "std_reward": 134.00062015952173, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-24T14:08:19.315201"}
+{"env_id": "LunarLander-v2", "mean_reward": -192.94768600200433, "std_reward": 90.63363089849656, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-24T14:10:41.352440"}