Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -49.59 +/- 61.14
+      value: 56.93 +/- 37.27
       name: mean_reward
       verified: false
 ---
@@ -37,16 +37,16 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 500000
+'total_timesteps': 1000000
 'learning_rate': 0.0001
 'num_envs': 16
-'num_steps': 1024
+'num_steps': 2048
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.98
-'num_minibatches': 64
-'update_epochs': 16
+'num_minibatches': 128
+'update_epochs': 32
 'norm_adv': True
 'clip_coef': 0.05
 'clip_vloss': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'yuval6967/LunarLander-v2PPO'
-'batch_size': 16384
+'batch_size': 32768
 'minibatch_size': 256}
   ```
   

logs/events.out.tfevents.1685097861.2850cb3f29b2.37310.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7b295344028c2d04d54ad1e7fe1c42ab3096c197ffe0dc8edbc28d4316e80fe
+size 780458

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f94efd245a747c0ccb0b634a5629e5af417ce6c06f43091a220e1de4b720fe2f
+oid sha256:760139cf75adb3cd065d22029eaaa46738a220cbea03b3714f6ad1cce7ed9a76
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -49.58853985959958, "std_reward": 61.141176711995605, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T10:42:23.689720"}
+{"env_id": "LunarLander-v2", "mean_reward": 56.934094121960754, "std_reward": 37.269297025429516, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T11:02:34.301765"}