ZZVic/ppo-LunarLander-v2-unit8

PPO Agent Playing LunarLander-v2

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

Hyperparameters

{'env_id': 'LunarLander-v2'
'total_timesteps': 500000
'num_envs': 4
'num_steps': 128
'gamma': 0.99
'gae_lambda': 0.95
'num_minibatches': 4
'update_epochs': 4
'learning_rate': 0.00025
'clip_coef': 0.2
'ent_coef': 0.01
'vf_coef': 0.5
'max_grad_norm': 0.5
'anneal_lr': True
'clip_vloss': True
'seed': 1}