Population-Guided Parallel Policy Search for Reinforcement Learning

TL;DR

This paper introduces a population-guided parallel learning scheme for reinforcement learning that enhances policy search efficiency by sharing experience and guiding multiple learners with the best policy information, leading to improved performance.

Contribution

It proposes a novel population-guided parallel policy search method with theoretical guarantees and demonstrates its effectiveness by applying it to TD3, outperforming existing algorithms.

Findings

Outperforms state-of-the-art RL algorithms

Enables faster policy convergence

Effective in sparse reward environments

Abstract

In this paper, a new population-guided parallel learning scheme is proposed to enhance the performance of off-policy reinforcement learning (RL). In the proposed scheme, multiple identical learners with their own value-functions and policies share a common experience replay buffer, and search a good policy in collaboration with the guidance of the best policy information. The key point is that the information of the best policy is fused in a soft manner by constructing an augmented loss function for policy update to enlarge the overall search region by the multiple learners. The guidance by the previous best policy and the enlarged range enable faster and better policy search. Monotone improvement of the expected cumulative return by the proposed scheme is proved theoretically. Working algorithms are constructed by applying the proposed scheme to the twin delayed deep deterministic (TD3) policy gradient algorithm. Numerical results show that the constructed algorithm outperforms most of the current state-of-the-art RL algorithms, and the gain is significant in the case of sparse reward environment.