Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -95.72 +/- 18.04
+      value: -33.47 +/- 103.65
       name: mean_reward
       verified: false
 ---
@@ -39,15 +39,15 @@ model-index:
 'f': '/root/.local/share/jupyter/runtime/kernel-034b7df4-145b-4db4-9d09-b6d875ced33d.json'
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 0.01
+'learning_rate': 0.001
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
-'gae_lambda': 0.92
+'gae_lambda': 0.8
 'num_minibatches': 4
-'update_epochs': 1
+'update_epochs': 2
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True

logs/events.out.tfevents.1691896039.4c5d58e91a6c.225.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5da21966a325b5a417d4516c80811e6b47858c348328a424375797967f8380a9
+size 152299

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d538bc9a1eb6199bb73b7040be16f82d283cff319b1796d06045d8240a000ea
+oid sha256:b8dacc41dfb18aca3bc40ab6b16d5cd2e61ac8b6c6e19ce7e0332153a3e7c66d
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -95.71604316487536, "std_reward": 18.043357992945417, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T03:06:43.351432"}
+{"env_id": "LunarLander-v2", "mean_reward": -33.47175804657828, "std_reward": 103.64850620213647, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T03:09:26.683247"}