Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 8.81 +/- 69.55
+      value: -164.42 +/- 70.38
       name: mean_reward
       verified: false
 ---
@@ -38,13 +38,13 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 500000
-'learning_rate': 0.00025
-'num_envs': 4
-'num_steps': 128
+'learning_rate': 0.0003
+'num_envs': 16
+'num_steps': 1024
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
-'gae_lambda': 0.95
+'gamma': 0.999
+'gae_lambda': 0.98
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'itsdhanoob/cleanRlPPO-lunar_lander'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 16384
+'minibatch_size': 4096}
   ```
   

logs/events.out.tfevents.1707918178.0b5757c85070.10124.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f317c2e428cae882d1f9087bec8a3755edc251421b4d65c51d74f884252085ff
+size 601284

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6ca04aff66f64822aba97da008791460d2a13e5294599c0e9a57325ed9eacdb
+oid sha256:d8374edaaf6963c589e942b7f6e6734de8152e1075152bf569a4022089adbd40
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 8.807411337415015, "std_reward": 69.54521751358743, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-14T13:27:55.446478"}
+{"env_id": "LunarLander-v2", "mean_reward": -164.41853578840528, "std_reward": 70.38290400359136, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-14T13:46:03.124109"}