Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -61.38 +/- 60.45
+      value: -30.71 +/- 62.22
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 0.001
+'learning_rate': 0.0001
 'num_envs': 4
 'num_steps': 1024
 'anneal_lr': True
@@ -46,7 +46,7 @@ model-index:
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 64
-'update_epochs': 3
+'update_epochs': 10
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True

logs/events.out.tfevents.1691961898.bcadd1928d08.21874.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd3cfeb16a0184434ea5f64df54819e3ef4f91144850b696219ac0bb8f98fc5e
+size 93077

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2fdbfb297ddc1eb1046c5c8acd4b83e775c3dbeffd5a56ed9fae1d6682c0bdd
+oid sha256:03c8f06b84653f9dff38759608fc50ce11144e3d361c83796f4b8f828ce07209
 size 4285797

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -61.38445987678015, "std_reward": 60.45487578445967, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T21:22:40.716666"}
+{"env_id": "LunarLander-v2", "mean_reward": -30.70509965682088, "std_reward": 62.218942815470946, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T21:27:44.179539"}