dragovoid/ppo-LunarLander-v2-u8

PPO Agent Playing LunarLander-v2

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

Hyperparameters

{'gym_id': 'LunarLander-v2'
'env_id': 'LunarLander-v2'
'exp_name': 'experiment'
'seed': 1
'torch_deterministic': True
'cuda': True
'track': True
'num_envs': 4
'capture_video': False
'num_steps': 128
'batch_size': 512
'learning_rate': 0.00025
'total_timesteps': 50000
'anneal_lr': True
'gae': True
'gamma': 0.99
'gae_lambda': 0.95
'clip_vloss': True
'ent_coef': 0.01
'vf_coef': 0.5
'max_grad_norm': 0.5
'update_epochs': 4
'num_minibatches': 4
'minibatch_size': 128
'clip_coef': 0.2
'norm_adv': True
'target_kl': None
'repo_id': 'dragovoid/ppo-LunarLander-v2-u8'}