Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
  type: LunarLander-v2
  metrics:
  - type: mean_reward
- value: -198.93 +/- 138.92
+ value: -155.11 +/- 72.85
  name: mean_reward
  verified: false
 ---
@@ -38,15 +38,15 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 1e-05
+'learning_rate': 0.0001
 'num_envs': 4
-'num_steps': 2048
+'num_steps': 512
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
-'num_minibatches': 8
-'update_epochs': 10
+'num_minibatches': 16
+'update_epochs': 8
 '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': 'arhamk/ppo-LunarLander-v2-2'
-'batch_size': 8192
-'minibatch_size': 1024}
+'batch_size': 2048
+'minibatch_size': 128}
  ```
  

logs/events.out.tfevents.1718025415.887b5cfc0142.12337.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c4e0a68eeae56a1d1849a2dc6f13015d742b78716411a62bca9e228f90e17a6
+size 70975

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbdda57fcf2dccebfd2e45a58ccf4fcfd5c9b9049649eb63e9b4aeaac316fa57
+oid sha256:d6c5823477f6a37bd9194edb9f45af0d3606ab6a06ee10c233282eadf2a1d850
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -198.92899401262682, "std_reward": 138.91576028315262, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T13:14:39.301212"}
+{"env_id": "LunarLander-v2", "mean_reward": -155.10927752489494, "std_reward": 72.85296879332041, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T13:17:47.166457"}