Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -157.60 +/- 131.43
+      value: -161.46 +/- 76.33
       name: mean_reward
       verified: false
 ---
@@ -39,7 +39,7 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
 'learning_rate': 0.00025
-'num_envs': 4
+'num_envs': 8
 'num_steps': 1028
 'anneal_lr': True
 'gae': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'anrb205/u8_p1_ppo'
-'batch_size': 4112
-'minibatch_size': 1028}
+'batch_size': 8224
+'minibatch_size': 2056}
   ```
   

logs/events.out.tfevents.1677956347.bcf0fbd46106.8304.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a542f7e5bfd8ff9100f6cc92334cd8e089469d2a92edd03e76dc24c05ca63864
+size 66399

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:542bcaebabaa58cf7437ff7d4b4ec508910c65f85bd4f2e79954adaf1fc05e98
+oid sha256:88c4fad837d06a6f16915d28a8e88903cd88270bea16e52d5795b5568a6360f7
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -157.5956825673712, "std_reward": 131.4296491311496, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-04T18:55:53.732964"}
+{"env_id": "LunarLander-v2", "mean_reward": -161.4585794459183, "std_reward": 76.32968468658295, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-04T18:59:31.333458"}