paper-with-me

홈 › Papers

Sample efficient Quality Diversity for neural continuous control

2021-01-01 · Thomas Pierrot, Valentin Macé, Geoffrey Cideron, Nicolas Perrin, Karim Beguir, Olivier Sigaud

We propose a novel Deep Neuroevolution algorithm, QD-RL, that combines the strengths of off-policy reinforcement learning (RL) algorithms and Quality Diversity (QD) approaches to solve continuous control problems with neural controllers. The QD part contributes structural biases by decoupling the search for diversity from the search for high return, resulting in efficient management of the exploration-exploitation trade-off. The RL part contributes sample efficiency by relying on off-policy gradient-based updates of the agents. More precisely, we train a population of off-policy deep RL agents to simultaneously maximize diversity within the population and the return of each individual agent. QD-RL selects agents interchangeably from a Pareto front or from a Map-Elites grid, resulting in stable and efficient population updates. Our experiments on the AntMaze and AntTrap environments show that QD-RL can solve challenging exploration and control problems with deceptive rewards while being over 15 times more sample efficient than its evolutionary counterparts.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

continuous-controlContinuous ControlDiversityManagementReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Diversity Policy Gradient for Sample Efficient Quality-Diversity Optimization

2020-06-15 · NeurIPS 2021 12 · Thomas Pierrot, Valentin Macé, Félix Chalumeau, Arthur Flajolet 외

A fascinating aspect of nature lies in its ability to produce a large and diverse collection of organisms that are all high-performing in their niche. By contrast, most AI algorithms focus on finding a single efficient s…

continuous-controlContinuous ControlDiversityEvolutionary Algorithms

Point Cloud Generation with Continuous Conditioning

2022-02-17 · Larissa T. Triess, Andre Bühler, David Peter, Fabian B. Flohr 외

Generative models can be used to synthesize 3D objects of high quality and diversity. However, there is typically no control over the properties of the generated object.This paper proposes a novel generative adversarial …

Density EstimationDiversityGenerative Adversarial NetworkPoint Cloud Generation

Improving Generative Adversarial Networks via Adversarial Learning in Latent Space

2021-09-29 · Yang Li, Yichuan Mo, Liangliang Shi, Junchi Yan 외

Generative Adversarial Networks (GANs) have been widely studied as generative models, which map a latent distribution to the target distribution. Although many efforts have been made in terms of backbone architecture des…

Diversity

Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance

2024-10-17 · Jiwan Hur, Dong-Jae Lee, Gyojin Han, Jaehyun Choi 외

Masked generative models (MGMs) have shown impressive generative ability while providing an order of magnitude efficient sampling steps compared to continuous diffusion models. However, MGMs still underperform in image s…

DiversityImage Generationparameter-efficient fine-tuning

Understanding the Quality-Diversity Trade-off in Diffusion Language Models

2025-03-11 · Zak Buzzard

Diffusion models have seen immense success in modelling continuous data across a range of domains such as vision and audio. Despite the challenges of adapting diffusion models to discrete data, recent work explores their…

DiversityLanguage ModelingLanguage ModellingText Generation