Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 163.90 +/- 79.31
+      value: 81.36 +/- 48.53
       name: mean_reward
       verified: false
 ---
@@ -40,7 +40,7 @@ model-index:
 'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
-'num_steps': 256
+'num_steps': 512
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'gstaff/ppo-LunarLander-v2'
-'batch_size': 1024
-'minibatch_size': 256}
+'batch_size': 2048
+'minibatch_size': 512}
   ```
   

logs/events.out.tfevents.1677559445.7823c2c484d2.28048.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:038205ce9ff75743709dd488ff2f006483b2c65c8da6f47681f70dde10f1508e
+size 722326

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54600ebed561f0a38bb5150972e5e097a9df942c066ce89c8ae224d6a351fcc8
+oid sha256:ae0d6aa21e271da69955977a6403945a3d8a221472f1f4163801d505f7fb9ccf
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 163.90300436958563, "std_reward": 79.30561244288248, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-28T04:42:45.105000"}
+{"env_id": "LunarLander-v2", "mean_reward": 81.36156247394752, "std_reward": 48.533026380835885, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-28T05:04:05.542403"}