English
Related papers

Related papers: Reward Redistribution for CVaR MDPs using a Bellma…

200 papers

We study risk-sensitive reinforcement learning (RL) based on an entropic risk measure in episodic non-stationary Markov decision processes (MDPs). Both the reward functions and the state transition kernels are unknown and allowed to vary…

Machine Learning · Computer Science 2022-11-22 Yuhao Ding , Ming Jin , Javad Lavaei

Differentiable planning promises end-to-end differentiability and adaptivity. However, an issue prevents it from scaling up to larger-scale problems: they need to differentiate through forward iteration layers to compute gradients, which…

Machine Learning · Computer Science 2023-05-02 Linfeng Zhao , Huazhe Xu , Lawson L. S. Wong

Improving data utilization efficiency is critical for scaling reinforcement learning (RL) for long-horizon tasks where generating trajectories is expensive. However, the dominant RL methods for LLMs are largely on-policy: they update each…

In this paper, we present a discretization algorithm for finite horizon risk constrained dynamic programming algorithm in [Chow_Pavone_13]. Although in a theoretical standpoint, Bellman's recursion provides a systematic way to find optimal…

Optimization and Control · Mathematics 2015-01-12 Yin-Lam Chow , Marco Pavone

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

General function approximation is a powerful tool to handle large state and action spaces in a broad range of reinforcement learning (RL) scenarios. However, theoretical understanding of non-stationary MDPs with general function…

Machine Learning · Computer Science 2023-06-02 Songtao Feng , Ming Yin , Ruiquan Huang , Yu-Xiang Wang , Jing Yang , Yingbin Liang

In this paper, we study the stochastic combinatorial multi-armed bandit problem under semi-bandit feedback. While much work has been done on algorithms that optimize the expected reward for linear as well as some general reward functions,…

Machine Learning · Computer Science 2021-12-03 Shaarad Ayyagari , Ambedkar Dukkipati

Optimizing risk-averse objectives in discounted MDPs is challenging because most models do not admit direct dynamic programming equations and require complex history-dependent policies. In this paper, we show that the risk-averse {\em total…

Machine Learning · Computer Science 2025-07-15 Xihong Su , Julien Grand-Clément , Marek Petrik

Reinforcement fine-tuning with verifiable rewards (RLVR) has emerged as a powerful paradigm for equipping large vision-language models (LVLMs) with agentic capabilities such as tool use and multi-step reasoning. Despite striking empirical…

Machine Learning · Computer Science 2026-04-23 Carter Adams , Rafael Oliveira , Gabriel Almeida , Sofia Torres

Reinforcement learning algorithms in multi-agent systems deliver highly resilient and adaptable solutions for common problems in telecommunications,aerospace, and industrial robotics. However, achieving an optimal global goal remains a…

Multiagent Systems · Computer Science 2021-05-18 Changgang Zheng , Shufan Yang , Juan Parra-Ullauri , Antonio Garcia-Dominguez , Nelly Bencomo

In this paper we argue for the fundamental importance of the value distribution: the distribution of the random return received by a reinforcement learning agent. This is in contrast to the common approach to reinforcement learning which…

Machine Learning · Computer Science 2017-07-24 Marc G. Bellemare , Will Dabney , Rémi Munos

Off-policy Reinforcement Learning (RL) holds the promise of better data efficiency as it allows sample reuse and potentially enables safe interaction with the environment. Current off-policy policy gradient methods either suffer from high…

Machine Learning · Computer Science 2021-06-09 Samuele Tosatto , João Carvalho , Jan Peters

In reinforcement learning the Q-values summarize the expected future rewards that the agent will attain. However, they cannot capture the epistemic uncertainty about those rewards. In this work we derive a new Bellman operator with…

Machine Learning · Computer Science 2022-12-07 Brendan O'Donoghue

This paper analyzes finite state Markov Decision Processes (MDPs) with uncertain parameters in compact sets and re-examines results from robust MDP via set-based fixed point theory. To this end, we generalize the Bellman and policy…

Machine Learning · Computer Science 2023-08-09 Sarah H. Q. Li , Assalé Adjé , Pierre-Loïc Garoche , Behçet Açıkmeşe

We study multi-objective reinforcement learning with nonlinear preferences over trajectories. That is, we maximize the expected value of a nonlinear function over accumulated rewards (expected scalarized return or ESR) in a multi-objective…

Machine Learning · Computer Science 2025-02-19 Nianli Peng , Muhang Tian , Brandon Fain

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 propose a novel framework for risk-sensitive reinforcement learning (RSRL) that incorporates robustness against transition uncertainty. We define two distinct yet coupled risk measures: an inner risk measure addressing state and cost…

Risk Management · Quantitative Finance 2026-01-01 Shanyu Han , Yangbo He , Yang Liu

While reinforcement learning algorithms provide automated acquisition of optimal policies, practical application of such methods requires a number of design decisions, such as manually designing reward functions that not only define the…

Machine Learning · Computer Science 2022-12-29 Tim G. J. Rudner , Vitchyr H. Pong , Rowan McAllister , Yarin Gal , Sergey Levine

A Budgeted Markov Decision Process (BMDP) is an extension of a Markov Decision Process to critical applications requiring safety constraints. It relies on a notion of risk implemented in the shape of a cost signal constrained to lie below…

Machine Learning · Computer Science 2019-05-29 Nicolas Carrara , Edouard Leurent , Romain Laroche , Tanguy Urvoy , Odalric-Ambrym Maillard , Olivier Pietquin

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