Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -110.38 +/- 53.45
+      value: -157.60 +/- 131.43
       name: mean_reward
       verified: false
 ---
@@ -40,7 +40,7 @@ model-index:
 'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 4
-'num_steps': 128
+'num_steps': 1028
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'anrb205/u8_p1_ppo'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 4112
+'minibatch_size': 1028}
   ```
   

logs/events.out.tfevents.1677956119.bcf0fbd46106.7238.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:176298f461102502d17e2a556dcdb273320af45a9c00e786ede3efa315ae29fe
+size 71095

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3262cb9f8d71762568958150de91d2adbb7385c87e56d48030e8005230aa5d95
+oid sha256:542bcaebabaa58cf7437ff7d4b4ec508910c65f85bd4f2e79954adaf1fc05e98
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -110.38113800376807, "std_reward": 53.446245320428964, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-04T18:35:08.070239"}
+{"env_id": "LunarLander-v2", "mean_reward": -157.5956825673712, "std_reward": 131.4296491311496, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-04T18:55:53.732964"}