# Diverse Exploration via Conjugate Policies for Policy Gradient Methods

arXiv: https://arxiv.org/abs/1902.03633 · HTML: https://mlsanity.com/paper/1902.03633/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Feb 2019.

## Built on by (most cited first, 2 of 2)

- [Adaptable Agent Populations via a Generative Model of Policies](https://mlsanity.com/paper/2107.07506/) (2021)
- [Beyond Rewards: a Hierarchical Perspective on Offline Multiagent Behavioral Analysis](https://mlsanity.com/paper/2206.09046/) (2022)

## Abstract (arXiv)

We address the challenge of effective exploration while maintaining good performance in policy gradient methods. As a solution, we propose diverse exploration (DE) via conjugate policies. DE learns and deploys a set of conjugate policies which can be conveniently generated as a byproduct of conjugate gradient descent. We provide both theoretical and empirical results showing the effectiveness of DE at achieving exploration, improving policy performance, and the advantage of DE over exploration by random policy perturbations.