paper-with-me

Papers

BiERL: A Meta Evolutionary Reinforcement Learning Framework via Bilevel Optimization

2023-08-01 · Junyi Wang, Yuanyang Zhu, Zhi Wang, Yan Zheng, Jianye Hao, Chunlin Chen

Evolutionary reinforcement learning (ERL) algorithms recently raise attention in tackling complex reinforcement learning (RL) problems due to high parallelism, while they are prone to insufficient exploration or model collapse without carefully tuning hyperparameters (aka meta-parameters). In the paper, we propose a general meta ERL framework via bilevel optimization (BiERL) to jointly update hyperparameters in parallel to training the ERL model within a single agent, which relieves the need for prior domain knowledge or costly optimization procedure before model deployment. We design an elegant meta-level architecture that embeds the inner-level's evolving experience into an informative population representation and introduce a simple and feasible evaluation of the meta-level fitness function to facilitate learning efficiency. We perform extensive experiments in MuJoCo and Box2D tasks to verify that as a general framework, BiERL outperforms various baselines and consistently improves the learning performance for a diversity of ERL algorithms.

📄 PDF Abstract BibTeX arXiv:2308.01207

Code (1)

chriswang98sz/bierl 공식 구현 pytorch

Tasks

Bilevel OptimizationDiversityMuJoCoreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

A Review on Bilevel Optimization: From Classical to Evolutionary Approaches and Applications

2017-05-17 · Ankur Sinha, Pekka Malo, Kalyanmoy Deb

Bilevel optimization is defined as a mathematical program, where an optimization problem contains another optimization problem as a constraint. These problems have received significant attention from the mathematical pro…

Bilevel OptimizationEvolutionary Algorithms

Adversarial Co-Evolution of Malware and Detection Models: A Bilevel Optimization Perspective

2026-04-24 · Olha Jurečková, Martin Jureček, Matouš Kozák, Róbert Lórencz arxiv

Machine learning-based malware detectors are increasingly vulnerable to adversarial examples. Traditional defenses, such as one-shot adversarial training, often fail against adaptive attackers who use reinforcement learn…

Reinforcement LearningBilevel OptimizationMalware Detection

Sample Complexity Analysis for Constrained Bilevel Reinforcement Learning

2026-01-30 · Naman Saxena, Vaneet Aggarwal arxiv

Several important problem settings within the literature of reinforcement learning (RL), such as meta-learning, hierarchical learning, and RL from human feedback (RL-HF), can be modelled as bilevel RL problems. A lot has…

Reinforcement Learning

Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator

2024-10-13 · Siyuan Xu, Minghui Zhu

Meta-reinforcement learning (Meta-RL) has attracted attention due to its capability to enhance reinforcement learning (RL) algorithms, in terms of data efficiency and generalizability. In this paper, we develop a bilevel…

AllBilevel OptimizationMeta Reinforcement Learningreinforcement-learning+2

Provably Faster Algorithms for Bilevel Optimization and Applications to Meta-Learning

2020-09-28 · Kaiyi Ji, Junjie Yang, Yingbin Liang

Bilevel optimization has arisen as a powerful tool for many machine learning problems such as meta-learning, hyperparameter optimization, and reinforcement learning. In this paper, we investigate the nonconvex-strongly-c…

Bilevel OptimizationHyperparameter OptimizationMeta-Learning