Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -206.42 +/- 95.17
+      value: -112.91 +/- 61.09
       name: mean_reward
       verified: false
 ---
@@ -39,19 +39,19 @@ model-index:
 'f': '/root/.local/share/jupyter/runtime/kernel-034b7df4-145b-4db4-9d09-b6d875ced33d.json'
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 0.0004
+'learning_rate': 0.0003
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
-'gae_lambda': 0.95
+'gae_lambda': 0.92
 'num_minibatches': 4
 'update_epochs': 1
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
-'ent_coef': 0.0005
+'ent_coef': 5e-05
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None

logs/events.out.tfevents.1691895677.4c5d58e91a6c.225.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56dab7fc08f98a7aa1d7515ce7e384301e1353acb94077433fce6ece6a6640ce
+size 220804

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9996801abd03add207198d5262985244cea04cc33a26289b3ca513c06f909138
+oid sha256:abfc5d589874b79115d1d6c6f538db925b7f15ab241296e6a93e71d8c3bdfbd4
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -206.42487658721757, "std_reward": 95.16599009967193, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:56:21.720477"}
+{"env_id": "LunarLander-v2", "mean_reward": -112.9129916957854, "std_reward": 61.0879027725272, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T03:02:37.852571"}