def ppo()

in safe_rl/pg/algos.py [0:0]

• 9 lines of code
• 1 McCabe index (conditional complexity)

def ppo(**kwargs):
    ppo_kwargs = dict(
                    reward_penalized=False,
                    objective_penalized=False,
                    learn_penalty=False,
                    penalty_param_loss=False  # Irrelevant in unconstrained
                    )
    agent = PPOAgent(**ppo_kwargs)
    run_polopt_agent(agent=agent, **kwargs)