Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 81.36 +/- 48.53
+      value: 142.90 +/- 32.98
       name: mean_reward
       verified: false
 ---
@@ -40,12 +40,12 @@ model-index:
 'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
-'num_steps': 512
+'num_steps': 1024
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
 'gae_lambda': 0.98
-'num_minibatches': 4
+'num_minibatches': 64
 'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'gstaff/ppo-LunarLander-v2'
-'batch_size': 2048
-'minibatch_size': 512}
+'batch_size': 4096
+'minibatch_size': 64}
   ```
   

logs/events.out.tfevents.1677563857.7823c2c484d2.46649.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c2c114c7ab0232c9770957cf7b7a9efd43b07bbeb835108221962e05bbfb0c1
+size 341243

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae0d6aa21e271da69955977a6403945a3d8a221472f1f4163801d505f7fb9ccf
+oid sha256:600b19d8910768527f5427b09f62ecdd41fc4cc73a5320f119473439b9e97fc6
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 81.36156247394752, "std_reward": 48.533026380835885, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-28T05:04:05.542403"}
+{"env_id": "LunarLander-v2", "mean_reward": 142.8957722429635, "std_reward": 32.97835325255021, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-28T06:27:01.482314"}