def cpo()

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

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

def cpo(**kwargs):
    cpo_kwargs = dict(
                    reward_penalized=False,  # Irrelevant in CPO
                    objective_penalized=False,  # Irrelevant in CPO
                    learn_penalty=False,  # Irrelevant in CPO
                    penalty_param_loss=False  # Irrelevant in CPO
                    )
    agent = CPOAgent(**cpo_kwargs)
    run_polopt_agent(agent=agent, **kwargs)