garage.np.algos.cma_es

Covariance Matrix Adaptation Evolution Strategy.

class CMAES(env_spec, policy, sampler, n_samples, discount=0.99, sigma0=1.0)

Bases: garage.np.algos.rl_algorithm.RLAlgorithm

Inheritance diagram of garage.np.algos.cma_es.CMAES

Covariance Matrix Adaptation Evolution Strategy.

Note

The CMA-ES method can hardly learn a successful policy even for simple task. It is still maintained here only for consistency with original rllab paper.

Parameters
train(self, trainer)

Initialize variables and start training.

Parameters

trainer (Trainer) – Trainer is passed to give algorithm the access to trainer.step_epochs(), which provides services such as snapshotting and sampler control.

Returns

The average return in last epoch cycle.

Return type

float