Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -121.55 +/- 91.05
+      value: -145.70 +/- 92.39
       name: mean_reward
       verified: false
 ---
@@ -31,22 +31,22 @@ model-index:
   {'exp_name': 'ppo'
 'env_id': 'LunarLander-v2'
 'learning_rate': 0.00025
-'seed': 1
-'total_timesteps': 50000
+'seed': 2024
+'total_timesteps': 200000
 'torch_deterministic': True
 'cuda': True
 'track': False
 'wandb_project_name': 'ppo-implementation-details'
 'wandb_entity': None
 'capture_video': False
-'num_envs': 4
-'num_steps': 128
+'num_envs': 10
+'num_steps': 250
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 4
-'update_epochs': 4
+'update_epochs': 6
 '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': 'LMrilo/ppo-LunarLander-v2-unit8'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 2500
+'minibatch_size': 625}
   ```
   

logs/events.out.tfevents.1717796049.b38a8e8f1437.5626.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b8462d1db80e679fbeede40f0cf81704a23c72cbf700bc1fdf8602bb3912f5d
+size 245670

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
+oid sha256:cc1011f992015587f264b1373ba82d5cdda8d549ae3ac0c3e24cee35dce8f2d4
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -121.55085943831887, "std_reward": 91.04951363933048, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-07T21:27:48.805070"}
+{"env_id": "LunarLander-v2", "mean_reward": -145.70115343018804, "std_reward": 92.3877427978616, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-07T21:35:42.074089"}