English
Related papers

Related papers: Risk-averse Total-reward MDPs with ERM and EVaR

200 papers

For continuing tasks, average cost Markov decision processes have well-documented value and can be solved using efficient algorithms. However, it explicitly assumes that the agent is risk-neutral. In this work, we extend risk-neutral…

Machine Learning · Computer Science 2025-12-23 Weikai Wang , Erick Delage

In this paper, we consider Markov Decision Processes (MDPs) with error states. Error states are those states entering which is undesirable or dangerous. We define the risk with respect to a policy as the probability of entering such a state…

Machine Learning · Computer Science 2011-09-13 P. Geibel , F. Wysotzki

Reward-free exploration is a reinforcement learning setting studied by Jin et al. (2020), who address it by running several algorithms with regret guarantees in parallel. In our work, we instead give a more natural adaptive approach for…

Machine Learning · Computer Science 2020-10-08 Emilie Kaufmann , Pierre Ménard , Omar Darwiche Domingues , Anders Jonsson , Edouard Leurent , Michal Valko

This paper provides conditions under which total-cost and average-cost Markov decision processes (MDPs) can be reduced to discounted ones. Results are given for transient total-cost MDPs with tran- sition rates whose values may be greater…

Optimization and Control · Mathematics 2017-05-04 Eugene A. Feinberg , Jefferson Huang

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…

Computation and Language · Computer Science 2026-03-03 Ruoxi Cheng , Haoxuan Ma , Weixin Wang , Ranjie Duan , Jiexi Liu , Xiaoshuang Jia , Simeng Qin , Xiaochun Cao , Yang Liu , Xiaojun Jia

We study the risk-sensitive exponential cost MDP formulation and develop a trajectory-based gradient algorithm to find the stationary point of the cost associated with a set of parameterized policies. We derive a formula that can be used to…

Systems and Control · Electrical Eng. & Systems 2022-08-31 Mehrdad Moharrami , Yashaswini Murthy , Arghyadip Roy , R. Srikant

There has been growing progress on theoretical analyses for provably efficient learning in MDPs with linear function approximation, but much of the existing work has made strong assumptions to enable exploration by conventional exploration…

Machine Learning · Computer Science 2020-10-23 Andrea Zanette , Alessandro Lazaric , Mykel J. Kochenderfer , Emma Brunskill

We study the problem of reinforcement learning in infinite-horizon discounted linear Markov decision processes (MDPs), and propose the first computationally efficient algorithm achieving rate-optimal regret guarantees in this setting. Our…

Machine Learning · Computer Science 2026-03-16 Antoine Moulin , Gergely Neu , Luca Viano

We investigate the ergodic problem of growth-rate maximization under a class of risk constraints in the context of incomplete, It\^{o}-process models of financial markets with random ergodic coefficients. Including {\em value-at-risk}…

Portfolio Management · Quantitative Finance 2008-12-02 Traian A. Pirvu , Gordan Zitkovic

In this work, we propose a novel inverse reinforcement learning (IRL) algorithm for constrained Markov decision process (CMDP) problems. In standard IRL problems, the inverse learner or agent seeks to recover the reward function of the MDP,…

Machine Learning · Computer Science 2024-01-08 Nirjhar Das , Arpan Chattopadhyay

Probabilistic learning to rank (LTR) has been the dominating approach for optimizing the ranking metric, but cannot maximize long-term rewards. Reinforcement learning models have been proposed to maximize user long-term rewards by…

Machine Learning · Computer Science 2024-01-18 Teng Xiao , Suhang Wang

We present a method for a certain class of Markov Decision Processes (MDPs) that can relate the optimal policy back to one or more reward sources in the environment. For a given initial state, without fully computing the value function,…

Machine Learning · Computer Science 2018-06-12 Josh Bertram , Peng Wei

Many real-world human behaviors can be characterized as a sequential decision making processes, such as urban travelers choices of transport modes and routes (Wu et al. 2017). Differing from choices controlled by machines, which in general…

Artificial Intelligence · Computer Science 2019-07-12 Guojun Wu , Yanhua Li , Zhenming Liu , Jie Bao , Yu Zheng , Jieping Ye , Jun Luo

In dynamic programming (DP) and reinforcement learning (RL), an agent learns to act optimally in terms of expected long-term return by sequentially interacting with its environment modeled by a Markov decision process (MDP). More generally…

Machine Learning · Computer Science 2022-01-03 Mastane Achab , Gergely Neu

RL with Verifiable Rewards (RLVR) has emerged as a promising paradigm for improving the reasoning abilities of large language models (LLMs). Current methods rely primarily on policy optimization frameworks like PPO and GRPO, which follow…

Machine Learning · Computer Science 2025-09-30 Haoran He , Yuxiao Ye , Qingpeng Cai , Chen Hu , Binxing Jiao , Daxin Jiang , Ling Pan

Markov decision processes (MDPs) are standard models for probabilistic systems with non-deterministic behaviours. Long-run average rewards provide a mathematically elegant formalism for expressing long term performance. Value iteration (VI)…

Systems and Control · Computer Science 2017-09-01 Pranav Ashok , Krishnendu Chatterjee , Przemyslaw Daca , Jan Křetínský , Tobias Meggendorfer

The specification of aMarkov decision process (MDP) can be difficult. Reward function specification is especially problematic; in practice, it is often cognitively complex and time-consuming for users to precisely specify rewards. This work…

Artificial Intelligence · Computer Science 2012-05-14 Kevin Regan , Craig Boutilier

Empirical Risk Minimization (ERM) based machine learning algorithms have suffered from weak generalization performance on data obtained from out-of-distribution (OOD). To address this problem, Invariant Risk Minimization (IRM) objective was…

Machine Learning · Computer Science 2021-03-25 Jun-Hyun Bae , Inchul Choi , Minho Lee

By adopting a distributional viewpoint on law-invariant convex risk measures, we construct dynamics risk measures (DRMs) at the distributional level. We then apply these DRMs to investigate Markov decision processes, incorporating latent…

Optimization and Control · Mathematics 2024-04-24 Ziteng Cheng , Sebastian Jaimungal

In this paper, we study risk-sensitive Reinforcement Learning (RL), focusing on the objective of Conditional Value at Risk (CVaR) with risk tolerance $\tau$. Starting with multi-arm bandits (MABs), we show the minimax CVaR regret rate is…

Machine Learning · Computer Science 2023-05-26 Kaiwen Wang , Nathan Kallus , Wen Sun