中文
相关论文

相关论文: Malliavin Calculus for Counterfactual Gradient Est…

200 篇论文

As AI systems become increasingly autonomous, aligning their decision-making to human preferences is essential. In domains like autonomous driving or robotics, it is impossible to write down the reward function representing these…

Offline inverse reinforcement learning (Offline IRL) aims to recover the structure of rewards and environment dynamics that underlie observed actions in a fixed, finite set of demonstrations from an expert agent. Accurate models of…

机器学习 · 计算机科学 2024-03-01 Siliang Zeng , Chenliang Li , Alfredo Garcia , Mingyi Hong

Inverse Reinforcement Learning (IRL) is the task of learning a single reward function given a Markov Decision Process (MDP) without defining the reward function, and a set of demonstrations generated by humans/experts. However, in practice,…

人工智能 · 计算机科学 2017-12-18 Siddharthan Rajasekaran , Jinwei Zhang , Jie Fu

The alignment of large language models (LLMs) is crucial for generating helpful and harmless content. Existing approaches leverage preference-based human feedback data to learn the reward function and align the LLM with the feedback data.…

机器学习 · 计算机科学 2024-11-15 Yuang Cai , Yuyu Yuan , Jinsheng Shi , Qinhong Lin

We consider the problem of recovering an expert's reward function with inverse reinforcement learning (IRL) when there are missing/incomplete state-action pairs or observations in the demonstrated trajectories. This issue of missing…

机器学习 · 计算机科学 2019-11-19 Tien Mai , Quoc Phong Nguyen , Kian Hsiang Low , Patrick Jaillet

Bayesian inference over the reward presents an ideal solution to the ill-posed nature of the inverse reinforcement learning problem. Unfortunately current methods generally do not scale well beyond the small tabular setting due to the need…

机器学习 · 计算机科学 2021-03-15 Alex J. Chan , Mihaela van der Schaar

Inverse Reinforcement Learning (IRL) techniques deal with the problem of deducing a reward function that explains the behavior of an expert agent who is assumed to act optimally in an underlying unknown task. In several problems of…

机器学习 · 计算机科学 2024-01-09 Riccardo Poiani , Gabriele Curti , Alberto Maria Metelli , Marcello Restelli

Inverse reinforcement learning (IRL), which infers reward functions from demonstrations, is a valuable tool for modeling and understanding decision-making behavior. Many variants of IRL have been developed to capture complexities of human…

机器学习 · 计算机科学 2026-05-14 Leo Benac , Abhishek Sharma , Alihan Huyuk , Finale Doshi-Velez

Trajectory prediction for surrounding agents is a challenging task in autonomous driving due to its inherent uncertainty and underlying multimodality. Unlike prevailing data-driven methods that primarily rely on supervised learning, in this…

计算机视觉与模式识别 · 计算机科学 2025-06-27 Muleilan Pei , Shaoshuai Shi , Lu Zhang , Peiliang Li , Shaojie Shen

Inverse Reinforcement Learning (IRL) aims to reconstruct the reward function from expert demonstrations to facilitate policy learning, and has demonstrated its remarkable success in imitation learning. To promote expert-like behavior,…

机器学习 · 计算机科学 2023-06-16 Shunyu Liu , Yunpeng Qing , Shuqi Xu , Hongyan Wu , Jiangtao Zhang , Jingyuan Cong , Tianhao Chen , Yunfu Liu , Mingli Song

This article studies inverse reinforcement learning (IRL) for the stochastic linear-quadratic optimal control problem, where two agents are considered. A learner agent does not know the expert agent's performance cost function, but it…

最优化与控制 · 数学 2024-05-28 Zhongshi Sun , Guangyan Jia

Inverse reinforcement learning (IRL) offers a powerful and general framework for learning humans' latent preferences in route recommendation, yet no approach has successfully addressed planetary-scale problems with hundreds of millions of…

Imitation learning is well-suited for robotic tasks where it is difficult to directly program the behavior or specify a cost for optimal control. In this work, we propose a method for learning the reward function (and the corresponding…

机器学习 · 计算机科学 2021-01-01 Tianwei Ni , Harshit Sikchi , Yufei Wang , Tejus Gupta , Lisa Lee , Benjamin Eysenbach

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

One typical assumption in inverse reinforcement learning (IRL) is that human experts act to optimize the expected utility of a stochastic cost with a fixed distribution. This assumption deviates from actual human behaviors under ambiguity.…

机器学习 · 计算机科学 2019-09-25 Rui Chen , Wenshuo Wang , Zirui Zhao , Ding Zhao

This work aims to tackle a major challenge in offline Inverse Reinforcement Learning (IRL), namely the reward extrapolation error, where the learned reward function may fail to explain the task correctly and misguide the agent in unseen…

机器学习 · 计算机科学 2023-02-22 Sheng Yue , Guanbo Wang , Wei Shao , Zhaofeng Zhang , Sen Lin , Ju Ren , Junshan Zhang

We propose a new approach to inverse reinforcement learning (IRL) based on the deep Gaussian process (deep GP) model, which is capable of learning complicated reward structures with few demonstrations. Our model stacks multiple latent GP…

机器学习 · 计算机科学 2017-05-08 Ming Jin , Andreas Damianou , Pieter Abbeel , Costas Spanos

Inverse reinforcement learning (IRL) is typically formulated as maximizing entropy subject to matching the distribution of expert trajectories. Classical (dual-ascent) IRL guarantees monotonic performance improvement but requires fully…

机器学习 · 计算机科学 2026-05-13 Anish Diwan , Davide Tateo , Christopher E. Mower , Haitham Bou-Ammar , Jan Peters , Oleg Arenz

Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with reinforcement learning) or reward-free (directly fine-tuning…

计算与语言 · 计算机科学 2026-03-03 Ruoxi Cheng , Haoxuan Ma , Weixin Wang , Ranjie Duan , Jiexi Liu , Xiaoshuang Jia , Simeng Qin , Xiaochun Cao , Yang Liu , Xiaojun Jia

Inverse Reinforcement Learning (IRL) is a powerful paradigm for inferring a reward function from expert demonstrations. Many IRL algorithms require a known transition model and sometimes even a known expert policy, or they at least require…

机器学习 · 计算机科学 2023-08-23 David Lindner , Andreas Krause , Giorgia Ramponi