MartinVanBuren/ppo-unit-8-1

PPO Agent Playing LunarLander-v2

This is a trained model of a PPO agent playing LunarLander-v2.

Hyperparameters

{'seed': 42069
'capture_video': True
'learning_rate': 0.0003
'eps': 1e-05
'num_steps': 1024
'total_timesteps': 2500000
'anneal_lr': True
'gae': True
'gamma': 0.999
'gae_lambda': 0.95
'update_epochs': 4
'num_minibatches': 4
'clip_coef': 0.2
'norm_adv': True
'clip_vloss': True
'ent_coef': 0.01
'vf_coef': 0.5
'max_grad_norm': 0.5
'target_kl': None
'batch_size': 8192
'minibatch_size': 2048
'env_id': 'LunarLander-v2'}