paper-with-me

홈 › Papers

Pareto Inverse Reinforcement Learning for Diverse Expert Policy Generation

2024-08-22 · Woo Kyung Kim, Minjong Yoo, Honguk Woo

Data-driven offline reinforcement learning and imitation learning approaches have been gaining popularity in addressing sequential decision-making problems. Yet, these approaches rarely consider learning Pareto-optimal policies from a limited pool of expert datasets. This becomes particularly marked due to practical limitations in obtaining comprehensive datasets for all preferences, where multiple conflicting objectives exist and each expert might hold a unique optimization preference for these objectives. In this paper, we adapt inverse reinforcement learning (IRL) by using reward distance estimates for regularizing the discriminator. This enables progressive generation of a set of policies that accommodate diverse preferences on the multiple objectives, while using only two distinct datasets, each associated with a different expert preference. In doing so, we present a Pareto IRL framework (ParIRL) that establishes a Pareto policy set from these limited datasets. In the framework, the Pareto policy set is then distilled into a single, preference-conditioned diffusion model, thus allowing users to immediately specify which expert's patterns they prefer. Through experiments, we show that ParIRL outperforms other IRL algorithms for various multi-objective control tasks, achieving the dense approximation of the Pareto frontier. We also demonstrate the applicability of ParIRL with autonomous driving in CARLA.

📄 PDF Abstract BibTeX arXiv:2408.12110

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingDecision MakingImitation Learningreinforcement-learningReinforcement LearningSequential Decision Making

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Entropy Regularization 설명 없음
PPO Proximal Policy Optimization, or PPO, is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable…
CARLA CARLA is an open-source simulator for autonomous driving research. CARLA has been developed from the ground up to support development, training, and validation of autonomous urban…
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learning

2017-09-20 · Peter Henderson, Wei-Di Chang, Pierre-Luc Bacon, David Meger 외

Reinforcement learning has shown promise in learning policies that can solve complex problems. However, manually specifying a good reward function can be difficult, especially for intricate tasks. Inverse reinforcement l…

continuous-controlContinuous ControlImitation Learningreinforcement-learning+3

Inverse Delayed Reinforcement Learning

2024-12-04 · Simon Sinong Zhan, Qingyuan Wu, Zhian Ruan, Frank Yang 외

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 b…

MuJoCoreinforcement-learningReinforcement Learning

Statistical analysis of Inverse Entropy-regularized Reinforcement Learning

2025-12-07 · Denis Belomestny, Alexey Naumov, Sergey Samsonov arxiv

Inverse reinforcement learning aims to infer the reward function that explains expert behavior observed through trajectories of state--action pairs. A long-standing difficulty in classical IRL is the non-uniqueness of th…

Reinforcement Learning

Off-Policy Adversarial Inverse Reinforcement Learning

2020-05-03 · ICML Workshop LifelongML 2020 7 · Samin Yeasar Arnob

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 …

continuous-controlContinuous ControlImitation Learningreinforcement-learning+3

Learning Causally Invariant Reward Functions from Diverse Demonstrations

2024-09-12 · Ivan Ovinnikov, Eugene Bykovets, Joachim M. Buhmann

Inverse reinforcement learning methods aim to retrieve the reward function of a Markov decision process based on a dataset of expert demonstrations. The commonplace scarcity and heterogeneous sources of such demonstratio…

reinforcement-learningReinforcement Learning