Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -65.89 +/- 48.70
+      value: -74.84 +/- 33.01
       name: mean_reward
       verified: false
 ---
@@ -36,18 +36,18 @@ model-index:
 'wandb_project_name': 'cleanRL'
 'wandb_entity': None
 'capture_video': False
-'f': '/root/.local/share/jupyter/runtime/kernel-13ae2347-2156-49eb-80c5-a8b483ae1b52.json'
+'f': '/root/.local/share/jupyter/runtime/kernel-034b7df4-145b-4db4-9d09-b6d875ced33d.json'
 'env_id': 'LunarLander-v2'
-'total_timesteps': 5000000
-'learning_rate': 0.00022
-'num_envs': 16
-'num_steps': 256
+'total_timesteps': 100000
+'learning_rate': 0.00024
+'num_envs': 4
+'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 4
-'update_epochs': 4
+'update_epochs': 2
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
@@ -56,7 +56,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'mgmeskill/ppo-LunarLander-v3'
-'batch_size': 4096
-'minibatch_size': 1024}
+'batch_size': 512
+'minibatch_size': 128}
   ```
   

logs/events.out.tfevents.1691893510.4c5d58e91a6c.225.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2859740c3ca6d49dfd7d33805c53edc3156da6c70edf5fe3fe148c51e07785cb
+size 213994

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15cb7f56f995a36665aa0d7fe1829234173cb37faa85c82c17de17df4a2b70ac
+oid sha256:fe4bad068f1aeeb787f57574e8a9a71540801921c50451557fa92b9e5101caf4
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -65.88774618288689, "std_reward": 48.70327928360739, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T01:12:02.509462"}
+{"env_id": "LunarLander-v2", "mean_reward": -74.8416016528234, "std_reward": 33.00754289204665, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:26:33.269902"}