Bias in Natural Actor-Critic Algorithms
نویسنده
چکیده
We show that two popular discounted reward natural actor-critics, NAC-LSTD and eNAC, follow biased estimates of the natural policy gradient. We derive the first unbiased discounted reward natural actor-critics using batch and iterative approaches to gradient estimation and prove their convergence to globally optimal policies for discrete problems and locally optimal policies for continuous problems. Finally, we argue that the bias makes the existing algorithms more appropriate for the average reward setting.
منابع مشابه
Projected Natural Actor-Critic
Natural actor-critics form a popular class of policy search algorithms for finding locally optimal policies for Markov decision processes. In this paper we address a drawback of natural actor-critics that limits their real-world applicability—their lack of safety guarantees. We present a principled algorithm for performing natural gradient descent over a constrained domain. In the context of re...
متن کاملIncremental Natural Actor-Critic Algorithms
We present four new reinforcement learning algorithms based on actor-critic and natural-gradient ideas, and provide their convergence proofs. Actor-critic reinforcement learning methods are online approximations to policy iteration in which the value-function parameters are estimated using temporal difference learning and the policy parameters are updated by stochastic gradient descent. Methods...
متن کاملApplying the Episodic Natural Actor-Critic Architecture to Motor Primitive Learning
In this paper, we investigate motor primitive learning with the Natural Actor-Critic approach. The Natural Actor-Critic consists out of actor updates which are achieved using natural stochastic policy gradients while the critic obtains the natural policy gradient by linear regression. We show that this architecture can be used to learn the “building blocks of movement generation”, called motor ...
متن کاملNatural actor-critic algorithms
We present four new reinforcement learning algorithms based on actor–critic, natural-gradient and function-approximation ideas, and we provide their convergence proofs. Actor–critic reinforcement learning methods are online approximations to policy iteration in which the value-function parameters are estimated using temporal difference learning and the policy parameters are updated by stochasti...
متن کاملNatural Actor-Critic
This paper investigates a novel model-free reinforcement learning architecture, the Natural Actor-Critic. The actor updates are based on stochastic policy gradients employing Amari’s natural gradient approach, while the critic obtains both the natural policy gradient and additional parameters of a value function simultaneously by linear regression. We show that actor improvements with natural p...
متن کامل