paper-with-me

Papers

Stein Variational Goal Generation for adaptive Exploration in Multi-Goal Reinforcement Learning

2022-06-14 · Nicolas Castanet, Sylvain Lamprier, Olivier Sigaud

In multi-goal Reinforcement Learning, an agent can share experience between related training tasks, resulting in better generalization for new tasks at test time. However, when the goal space has discontinuities and the reward is sparse, a majority of goals are difficult to reach. In this context, a curriculum over goals helps agents learn by adapting training tasks to their current capabilities. In this work we propose Stein Variational Goal Generation (SVGG), which samples goals of intermediate difficulty for the agent, by leveraging a learned predictive model of its goal reaching capabilities. The distribution of goals is modeled with particles that are attracted in areas of appropriate difficulty using Stein Variational Gradient Descent. We show that SVGG outperforms state-of-the-art multi-goal Reinforcement Learning methods in terms of success coverage in hard exploration problems, and demonstrate that it is endowed with a useful recovery property when the environment changes.

📄 PDF Abstract BibTeX arXiv:2206.06719

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Goal Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Branching Stein Variational Gradient Descent for sampling multimodal distributions

2025-06-16 · Isaias Banales, Arturo Jaramillo, Heli Ricalde Guerrero

We propose a novel particle-based variational inference method designed to work with multimodal distributions. Our approach, referred to as Branched Stein Variational Gradient Descent (BSVGD), extends the classical Stein…

Variational Inference

Stein Variational Policy Gradient

2017-04-07 · Yang Liu, Prajit Ramachandran, Qiang Liu, Jian Peng

Policy gradient methods have been successfully applied to many complex reinforcement learning problems. However, policy gradient methods suffer from high variance, slow convergence, and inefficient exploration. In this w…

Bayesian Inferencecontinuous-controlContinuous ControlPolicy Gradient Methods+3

Stein Variational Adaptive Importance Sampling

2017-04-18 · Jun Han, Qiang Liu

We propose a novel adaptive importance sampling algorithm which incorporates Stein variational gradient decent algorithm (SVGD) with importance sampling (IS). Our algorithm leverages the nonparametric transforms in SVGD …

Diagnostic

Sampling with Mirrored Stein Operators

2021-06-23 · ICLR 2022 4 · Jiaxin Shi, Chang Liu, Lester Mackey

We introduce a new family of particle evolution samplers suitable for constrained domains and non-Euclidean geometries. Stein Variational Mirror Descent and Mirrored Stein Variational Gradient Descent minimize the Kullba…

valid

Particle-based Variational Inference with Generalized Wasserstein Gradient Flow

2023-09-21 · NeurIPS 2023 11

Particle-based variational inference methods (ParVIs) such as Stein variational gradient descent (SVGD) update the particles based on the kernelized Wasserstein gradient flow for the Kullback-Leibler (KL) divergence. How…