EExe/my_ppo_LunarLand

PPO Agent Playing LunarLander-v2

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

Hyperparameters

{'exp_name': 'debug'
'gym_id': 'LunarLander-v2'
'hface_repo': 'EExe/my_ppo_LunarLand'
'learning_rate': 0.00025
'seed': 42
'total_timesteps': 2000000
'num_envs': 4
'num_steps': 1024
'gamma': 0.999
'gae_lambda': 0.98
'num_minibatches': 64
'num_epochs': 10
'clip_coeff': 0.2
'ent_coeff': 0.1
'vf_coeff': 0.1
'max_gradient_norm': 0.5
'target_kl': 0.015}