Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 20.19 +/- 120.39
+      value: 220.54 +/- 60.91
       name: mean_reward
       verified: false
 ---
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000000
-'learning_rate': 0.00025
+'total_timesteps': 200000
+'learning_rate': 0.005
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
@@ -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.1692163387.a2fbd87124af.6165.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10b7ff4d29bb43363f4176705ae7859cae097a2161902c810abc97c9cf841e5e
+size 278050

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16c14154a3239d4afb840cfc54bd5b1191d7ba55775f805d70c2dc0318a3d85c
+oid sha256:e564e430ae3cce0e7abe0aaa2b46941cdad3e92acf817a4070dc9414dbab0ee1
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 20.187857943734894, "std_reward": 120.38986526044974, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-16T04:19:41.345449"}
+{"env_id": "LunarLander-v2", "mean_reward": 220.54352927193767, "std_reward": 60.9144358174186, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-16T05:27:06.271444"}