Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -150.89 +/- 91.16
+      value: -131.20 +/- 95.30
       name: mean_reward
       verified: false
 ---
@@ -39,7 +39,7 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
 'learning_rate': 3e-05
-'num_envs': 32
+'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
 'gae': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'yuval6967/LunarLander-v2PPO'
-'batch_size': 4096
-'minibatch_size': 1024}
+'batch_size': 512
+'minibatch_size': 128}
   ```
   

logs/events.out.tfevents.1685095891.2850cb3f29b2.28846.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4631588e6a693fa7f0599d86ffe210a89a6756739f8512767d92ba4d9352f2b
+size 114415

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fc19ab586789f20095cd283ce156a9a8e7be03f6e49f4b2bb8a29b9402eb8fc
+oid sha256:29c6e25c4eb6cf4d491d438cc9082ac2c0675586c20e21f2bcfee8ab33b0c47a
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -150.89227915093468, "std_reward": 91.16428592119877, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T10:11:09.535079"}
+{"env_id": "LunarLander-v2", "mean_reward": -131.2006583423907, "std_reward": 95.30287141570705, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T10:12:32.686112"}