Efficient Exploration using Model-Based Quality-Diversity with Gradients

TL;DR

This paper introduces a model-based Quality-Diversity method that uses gradients and imagination-based perturbations to improve exploration and sample efficiency in reinforcement learning environments with deceptive and sparse rewards.

Contribution

It extends existing QD methods by incorporating gradient-based optimization and imagination-driven exploration, significantly enhancing sample efficiency and solution quality.

Findings

Maintains divergent search capabilities in deceptive environments.

Significantly improves sample efficiency over traditional QD methods.

Produces higher quality solutions with fewer samples.

Abstract

Exploration is a key challenge in Reinforcement Learning, especially in long-horizon, deceptive and sparse-reward environments. For such applications, population-based approaches have proven effective. Methods such as Quality-Diversity deals with this by encouraging novel solutions and producing a diversity of behaviours. However, these methods are driven by either undirected sampling (i.e. mutations) or use approximated gradients (i.e. Evolution Strategies) in the parameter space, which makes them highly sample-inefficient. In this paper, we propose a model-based Quality-Diversity approach. It extends existing QD methods to use gradients for efficient exploitation and leverage perturbations in imagination for efficient exploration. Our approach optimizes all members of a population simultaneously to maintain both performance and diversity efficiently by leveraging the effectiveness of QD algorithms as good data generators to train deep models. We demonstrate that it maintains the divergent search capabilities of population-based approaches on tasks with deceptive rewards while significantly improving their sample efficiency and quality of solutions.