Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -38.73 +/- 81.68
+      value: -50.09 +/- 113.07
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000000
+'total_timesteps': 500000
 'learning_rate': 5e-05
 'num_envs': 8
 'num_steps': 1024
@@ -45,7 +45,7 @@ model-index:
 'gae': True
 'gamma': 0.999
 'gae_lambda': 0.896973
-'num_minibatches': 500
+'num_minibatches': 128
 'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.384411
@@ -56,6 +56,6 @@ model-index:
 'target_kl': 0.01
 'repo_id': 'zzen0008/ppo-LunarLander-v2'
 'batch_size': 8192
-'minibatch_size': 16}
+'minibatch_size': 64}
   ```
   

logs/events.out.tfevents.1678610765.ZZDev.126235.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e27ab6b2149c67baa60f6d668b603da12c65dff27332f269283c6bbd9bbd664
+size 343014

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e84e760f93322f68788e57e5ee27d031093d2307b59143356acf6a3cf3900f3
+oid sha256:062579449773d86c85391bdd1b3e2095fec26c301b7cbe4b0b6ef262b8732d40
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -38.7280814098008, "std_reward": 81.6827708617197, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-12T19:19:27.574416"}
+{"env_id": "LunarLander-v2", "mean_reward": -50.08888548974316, "std_reward": 113.07297848822984, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-12T19:51:48.160348"}