Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -140.20 +/- 62.56
+      value: -132.29 +/- 99.32
       name: mean_reward
       verified: false
 ---
@@ -39,13 +39,13 @@ model-index:
 'f': '/root/.local/share/jupyter/runtime/kernel-034b7df4-145b-4db4-9d09-b6d875ced33d.json'
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 0.00016
+'learning_rate': 0.00022
 'num_envs': 4
 'num_steps': 192
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
-'gae_lambda': 0.92
+'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True

logs/events.out.tfevents.1691894959.4c5d58e91a6c.225.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35c5fd59e32aaab54b4691f29c1b7b7bd6440846e79da51e4370ea98e5b4ecb2
+size 187419

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdfa2029b0aefea0215b61fe163f1e53ff36690e3b2ce4534e8cdd6093c16207
+oid sha256:6fbad6a2fb836dbc3be939fac3f9e7ac223ee08e1191f2f0c71ae50b1e9a8c2f
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -140.20012366988448, "std_reward": 62.55615038566897, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:49:07.357596"}
+{"env_id": "LunarLander-v2", "mean_reward": -132.29429884868858, "std_reward": 99.31866957760028, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:50:43.663470"}