Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -149.62 +/- 69.77
+      value: -140.52 +/- 139.30
       name: mean_reward
       verified: false
 ---
@@ -37,25 +37,25 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 500000
-'learning_rate': 1e-05
-'num_envs': 8
-'num_steps': 128
+'total_timesteps': 50000
+'learning_rate': 0.00025
+'num_envs': 4
+'num_steps': 1024
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
-'gae_lambda': 0.95
+'gamma': 0.995
+'gae_lambda': 0.98
 'num_minibatches': 4
-'update_epochs': 5
+'update_epochs': 8
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
-'ent_coef': 0.01
+'ent_coef': 0.05
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'jfelgate/ppo-LunarLander-v2'
-'batch_size': 1024
-'minibatch_size': 256}
+'batch_size': 4096
+'minibatch_size': 1024}
   ```
   

logs/events.out.tfevents.1698072202.527fe3665085.23376.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56ec84c2da8a5ae7fd2cb6dfb30ce36fda4414474aeea18ad1b2e8b64bc213a9
+size 70530

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b1d5295d0f0a75b98170f907a71cb16c194d86cc49afd079f10c4ee8776f427
+oid sha256:1cbfaecbb24ac3ea65256e285fbc416819df587a8c6637a7ce8bed6a7d1acbaf
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -149.62111145713575, "std_reward": 69.77237910656221, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-23T14:36:56.923918"}
+{"env_id": "LunarLander-v2", "mean_reward": -140.5234187987159, "std_reward": 139.30437296107738, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-23T14:44:01.462272"}