Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -22.84 +/- 49.10
+      value: 41.45 +/- 84.63
       name: mean_reward
       verified: false
 ---
@@ -37,10 +37,10 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 500000
+'total_timesteps': 220000
 'learning_rate': 0.00025
-'num_envs': 8
-'num_steps': 128
+'num_envs': 4
+'num_steps': 64
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'egarciamartin/ppo-LunarLander-v2'
-'batch_size': 1024
-'minibatch_size': 256}
+'batch_size': 256
+'minibatch_size': 64}
   ```
   

logs/events.out.tfevents.1692790329.5efc425d6703.11025.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2afec6ea5902977fb8dcd337426cc089219b785f6f9d65e9383dbf480003b145
+size 545671

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e3c7f066a8a53c707eec177e22229fd1d0c34b94e953f13d52424b5507e3b35
+oid sha256:adffe372cbe9e8f0121202010629f71bb89269c3390b8c80fd24a501ba373ec4
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -22.838968788044514, "std_reward": 49.10013361300843, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-23T11:18:35.278779"}
+{"env_id": "LunarLander-v2", "mean_reward": 41.45210192531314, "std_reward": 84.62507045249505, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-23T11:38:00.348219"}