中文
相关论文

相关论文: Pareto Inverse Reinforcement Learning for Diverse …

200 篇论文

As generative agents become increasingly capable, alignment of their behavior with complex human values remains a fundamental challenge. Existing approaches often simplify human intent through reduction to a scalar reward, overlooking the…

机器学习 · 计算机科学 2025-07-30 Kalyan Cherukuri , Aarav Lala

Explicit engineering of reward functions for given environments has been a major hindrance to reinforcement learning methods. While Inverse Reinforcement Learning (IRL) is a solution to recover reward functions from demonstrations only,…

机器学习 · 计算机科学 2020-02-24 David Venuto , Jhelum Chakravorty , Leonard Boussioux , Junhao Wang , Gavin McCracken , Doina Precup

Inverse Reinforcement Learning (IRL) is attractive in scenarios where reward engineering can be tedious. However, prior IRL algorithms use on-policy transitions, which require intensive sampling from the current policy for stable and…

机器学习 · 计算机科学 2022-05-24 Hana Hoshino , Kei Ota , Asako Kanezaki , Rio Yokota

Multi-objective decision-making problems have emerged in numerous real-world scenarios, such as video games, navigation and robotics. Considering the clear advantages of Reinforcement Learning (RL) in optimizing decision-making processes,…

机器学习 · 计算机科学 2025-01-15 Erlong Liu , Yu-Chang Wu , Xiaobin Huang , Chengrui Gao , Ren-Jian Wang , Ke Xue , Chao Qian

Inverse Reinforcement Learning (IRL) -- the problem of learning reward functions from demonstrations of an \emph{expert policy} -- plays a critical role in developing intelligent systems. While widely used in applications, theoretical…

机器学习 · 统计学 2024-02-13 Lei Zhao , Mengdi Wang , Yu Bai

Adversarial Imitation Learning (AIL) is a class of algorithms in Reinforcement learning (RL), which tries to imitate an expert without taking any reward from the environment and does not provide expert behavior directly to the policy…

机器学习 · 计算机科学 2020-05-05 Samin Yeasar Arnob

Inverse reinforcement learning (IRL) aims to recover the reward function of an expert agent from demonstrations of behavior. It is well-known that the IRL problem is fundamentally ill-posed, i.e., many reward functions can explain the…

机器学习 · 计算机科学 2024-06-07 Filippo Lazzati , Mirco Mutti , Alberto Maria Metelli

Sequential decision making in the real world often requires finding a good balance of conflicting objectives. In general, there exist a plethora of Pareto-optimal policies that embody different patterns of compromises between objectives,…

机器学习 · 计算机科学 2024-10-08 Takuya Kanazawa , Chetan Gupta

Inverse Reinforcement Learning (IRL) has demonstrated effectiveness in a variety of imitation tasks. In this paper, we introduce an IRL framework designed to extract rewarding features from expert trajectories affected by delayed…

机器学习 · 计算机科学 2024-12-05 Simon Sinong Zhan , Qingyuan Wu , Zhian Ruan , Frank Yang , Philip Wang , Yixuan Wang , Ruochen Jiao , Chao Huang , Qi Zhu

Multi-objective reinforcement learning (MORL) provides an effective solution for decision-making problems involving conflicting objectives. However, achieving high-quality approximations to the Pareto policy set remains challenging,…

人工智能 · 计算机科学 2026-03-23 Tianmeng Hu , Biao Luo

Many imitation learning (IL) algorithms use inverse reinforcement learning (IRL) to infer a reward function that aligns with the demonstration. However, the inferred reward functions often fail to capture the underlying task objectives. In…

机器学习 · 计算机科学 2024-11-01 Weichao Zhou , Wenchao Li

Inverse Reinforcement Learning (IRL) learns an optimal policy, given some expert demonstrations, thus avoiding the need for the tedious process of specifying a suitable reward function. However, current methods are constrained by at least…

机器学习 · 计算机科学 2023-11-16 Pierre Le Pelletier de Woillemont , Rémi Labory , Vincent Corruble

Offline reinforcement learning (RL) optimizes the policy on a previously collected dataset without any interactions with the environment, yet usually suffers from the distributional shift problem. To mitigate this issue, a typical solution…

机器学习 · 计算机科学 2023-09-06 Qisen Yang , Shenzhi Wang , Qihang Zhang , Gao Huang , Shiji Song

Inverse Reinforcement Learning (IRL) learns a reward function to explain expert demonstrations. Modern IRL methods often use the adversarial (minimax) formulation that alternates between reward and policy optimization, which often lead to…

机器学习 · 计算机科学 2025-10-14 Yang Chen , Menglin Zou , Jiaqi Zhang , Yitan Zhang , Junyi Yang , Gael Gendron , Libo Zhang , Jiamou Liu , Michael J. Witbrock

Ensuring AI models align with human values is essential for their safety and functionality. Reinforcement learning from human feedback (RLHF) leverages human preferences to achieve this alignment. However, when preferences are sourced from…

机器学习 · 计算机科学 2025-02-10 Ryan Bahlous-Boldi , Li Ding , Lee Spector , Scott Niekum

Optimizing multiple objectives simultaneously is an important task for recommendation platforms to improve their performance. However, this task is particularly challenging since the relationships between different objectives are…

信息检索 · 计算机科学 2026-02-13 Pan Li , Alexander Tuzhilin

Multi-objective reinforcement learning (MORL) is a structured approach for optimizing tasks with multiple objectives. However, it often relies on pre-defined reward functions, which can be hard to design for balancing conflicting goals and…

机器学习 · 计算机科学 2025-07-21 Ni Mu , Yao Luan , Qing-Shan Jia

Deep Reinforcement Learning achieves very good results in domains where reward functions can be manually engineered. At the same time, there is growing interest within the community in using games based on Procedurally Content Generation…

机器学习 · 计算机科学 2020-12-07 Alessandro Sestini , Alexander Kuhnle , Andrew D. Bagdanov

Multi-objective reinforcement learning (MORL) approaches have emerged to tackle many real-world problems with multiple conflicting objectives by maximizing a joint objective function weighted by a preference vector. These approaches find…

机器学习 · 计算机科学 2023-05-31 Toygun Basaklar , Suat Gumussoy , Umit Y. Ogras

In this paper, the inverse reinforcement learning (IRL) problem is addressed to reconstruct the unknown cost function underlying an observed optimal policy in a model-free manner, whose online adaptation with completely off-policy system…

最优化与控制 · 数学 2025-11-20 Yibei Li , Yuexin Cao , Zhixin Liu , Lihua Xie
‹ 上一页 1 2 3 10 下一页 ›