Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -169.00 +/- 95.26
+      value: -149.18 +/- 101.74
       name: mean_reward
       verified: false
 ---
@@ -37,16 +37,16 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 10000
-'learning_rate': 0.00025
-'num_envs': 4
+'total_timesteps': 100000
+'learning_rate': 0.00027
+'num_envs': 6
 'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 4
-'update_epochs': 4
+'update_epochs': 5
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'DiegoT200/LunarLander_by_foot'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 768
+'minibatch_size': 192}
   ```
   

logs/events.out.tfevents.1713299917.e08a0c6dcd4a.9952.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e66611eb6d9d440b49306c3f1a0c6417a6ce99b071fd7aa4c6b56d10a2e0181
+size 173445

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ca6ea3b0fd92b136ad616613c468cc73aebe9336363bb2a29440710c7129995
+oid sha256:085270a4d9235397c7e2424a90ae93a1556379f35d236a9fb554d9078a7730dc
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -169.0030245958529, "std_reward": 95.2577166022909, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-16T20:36:37.462903"}
+{"env_id": "LunarLander-v2", "mean_reward": -149.17842990941386, "std_reward": 101.74279003897688, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-16T20:39:47.481591"}