DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Wentse, Huang, Shiyu, Chiang, Yuan, Pearce, Tim, Tu, Wei-Wei, Chen, Ting, Zhu, Jun
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916081641193472
author Chen, Wentse
Huang, Shiyu
Chiang, Yuan
Pearce, Tim
Tu, Wei-Wei
Chen, Ting
Zhu, Jun
author_facet Chen, Wentse
Huang, Shiyu
Chiang, Yuan
Pearce, Tim
Tu, Wei-Wei
Chen, Ting
Zhu, Jun
contents Most reinforcement learning algorithms seek a single optimal strategy that solves a given task. However, it can often be valuable to learn a diverse set of solutions, for instance, to make an agent's interaction with users more engaging, or improve the robustness of a policy to an unexpected perturbance. We propose Diversity-Guided Policy Optimization (DGPO), an on-policy algorithm that discovers multiple strategies for solving a given task. Unlike prior work, it achieves this with a shared policy network trained over a single run. Specifically, we design an intrinsic reward based on an information-theoretic diversity objective. Our final objective alternately constraints on the diversity of the strategies and on the extrinsic reward. We solve the constrained optimization problem by casting it as a probabilistic inference task and use policy iteration to maximize the derived lower bound. Experimental results show that our method efficiently discovers diverse strategies in a wide variety of reinforcement learning tasks. Compared to baseline methods, DGPO achieves comparable rewards, while discovering more diverse strategies, and often with better sample efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2207_05631
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization
Chen, Wentse
Huang, Shiyu
Chiang, Yuan
Pearce, Tim
Tu, Wei-Wei
Chen, Ting
Zhu, Jun
Machine Learning
Artificial Intelligence
Most reinforcement learning algorithms seek a single optimal strategy that solves a given task. However, it can often be valuable to learn a diverse set of solutions, for instance, to make an agent's interaction with users more engaging, or improve the robustness of a policy to an unexpected perturbance. We propose Diversity-Guided Policy Optimization (DGPO), an on-policy algorithm that discovers multiple strategies for solving a given task. Unlike prior work, it achieves this with a shared policy network trained over a single run. Specifically, we design an intrinsic reward based on an information-theoretic diversity objective. Our final objective alternately constraints on the diversity of the strategies and on the extrinsic reward. We solve the constrained optimization problem by casting it as a probabilistic inference task and use policy iteration to maximize the derived lower bound. Experimental results show that our method efficiently discovers diverse strategies in a wide variety of reinforcement learning tasks. Compared to baseline methods, DGPO achieves comparable rewards, while discovering more diverse strategies, and often with better sample efficiency.
title DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2207.05631