Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -124.99 +/- 51.52
+      value: -97.24 +/- 95.72
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128
@@ -48,7 +48,7 @@ model-index:
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.2
+'clip_coef': 0.1
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5

logs/events.out.tfevents.1677881879.abb6b13a8830.24231.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4469e8efea5fb239b309f2ed04b741d086b3241e94bc2162523d2c3ce74d6f0
+size 195138

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5e9ce03d0822fa676c2441e91b6cbe400b7044ebdce1219d828ebb28ca0f306
+oid sha256:fe57261ed966a304ab1a8f3b60f2b654ca6f806b561ecb78b470a4636fad974b
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -124.98524969915316, "std_reward": 51.52318512085027, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-03T21:56:56.309598"}
+{"env_id": "LunarLander-v2", "mean_reward": -97.23690290366798, "std_reward": 95.72363806402899, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-03T22:19:21.314177"}