English
Related papers

Related papers: Towards Global Optimality for Practical Average Re…

200 papers

This work examines average-reward reinforcement learning with general policy parametrization. Existing state-of-the-art (SOTA) guarantees for this problem are either suboptimal or hindered by several challenges, including poor scalability…

Machine Learning · Computer Science 2025-05-07 Swetha Ganesh , Washim Uddin Mondal , Vaneet Aggarwal

Many existing reinforcement learning (RL) methods employ stochastic gradient iteration on the back end, whose stability hinges upon a hypothesis that the data-generating process mixes exponentially fast with a rate parameter that appears in…

Machine Learning · Computer Science 2023-02-02 Wesley A. Suttle , Amrit Singh Bedi , Bhrij Patel , Brian M. Sadler , Alec Koppel , Dinesh Manocha

Reinforcement learning with multiple, potentially conflicting objectives is pervasive in real-world applications, while this problem remains theoretically under-explored. This paper tackles the multi-objective reinforcement learning (MORL)…

Machine Learning · Computer Science 2024-05-10 Tianchen Zhou , FNU Hairi , Haibo Yang , Jia Liu , Tian Tong , Fan Yang , Michinari Momma , Yan Gao

Option-critic learning is a general-purpose reinforcement learning (RL) framework that aims to address the issue of long term credit assignment by leveraging temporal abstractions. However, when dealing with extended timescales, discounting…

Machine Learning · Computer Science 2019-11-21 Akshay Dharmavaram , Matthew Riemer , Shalabh Bhatnagar

We study multi-agent reinforcement learning (MARL) in a stochastic network of agents. The objective is to find localized policies that maximize the (discounted) global reward. In general, scalability is a challenge in this setting because…

Machine Learning · Computer Science 2021-11-03 Yiheng Lin , Guannan Qu , Longbo Huang , Adam Wierman

We propose a new algorithm, Mean Actor-Critic (MAC), for discrete-action continuous-state reinforcement learning. MAC is a policy gradient algorithm that uses the agent's explicit representation of all action values to estimate the gradient…

We present the first finite time global convergence analysis of policy gradient in the context of infinite horizon average reward Markov decision processes (MDPs). Specifically, we focus on ergodic tabular MDPs with finite state and action…

Machine Learning · Computer Science 2024-03-12 Navdeep Kumar , Yashaswini Murthy , Itai Shufaro , Kfir Y. Levy , R. Srikant , Shie Mannor

In tabular multi-agent reinforcement learning with average-cost criterion, a team of agents sequentially interacts with the environment and observes local incentives. We focus on the case that the global reward is a sum of local rewards,…

Optimization and Control · Mathematics 2021-10-26 Alec Koppel , Amrit Singh Bedi , Bhargav Ganguly , Vaneet Aggarwal

We derive and analyze learning algorithms for apprenticeship learning, policy evaluation, and policy gradient for average reward criteria. Existing algorithms explicitly require an upper bound on the mixing time. In contrast, we build on…

Machine Learning · Computer Science 2020-06-23 Tom Zahavy , Alon Cohen , Haim Kaplan , Yishay Mansour

In many sequential decision-making problems we may want to manage risk by minimizing some measure of variability in rewards in addition to maximizing a standard criterion. Variance related risk measures are among the most common…

Machine Learning · Computer Science 2015-03-19 Prashanth L. A. , Mohammad Ghavamzadeh

We study infinite-horizon Constrained Markov Decision Processes (CMDPs) with general policy parameterizations and multi-layer neural network critics. Existing theoretical analyses for constrained reinforcement learning largely rely on…

Machine Learning · Computer Science 2026-03-10 Anirudh Satheesh , Pankaj Kumar Barman , Washim Uddin Mondal , Vaneet Aggarwal

In graph-structured multi-agent reinforcement learning (MARL) adversarial tasks such as pursuit and confrontation, agents must coordinate under highly dynamic interactions, where sparse rewards hinder efficient policy learning. We propose…

Machine Learning · Computer Science 2025-11-12 Ruochuan Shi , Runyu Lu , Yuanheng Zhu , Dongbin Zhao

We consider an agent who is involved in a Markov decision process and receives a vector of outcomes every round. Her objective is to maximize a global concave reward function on the average vectorial outcome. The problem models applications…

Machine Learning · Computer Science 2019-05-17 Wang Chi Cheung

Markov Decision Processes (MDPs), the mathematical framework underlying most algorithms in Reinforcement Learning (RL), are often used in a way that wrongfully assumes that the state of an agent's environment does not change during action…

Machine Learning · Computer Science 2019-12-13 Simon Ramstedt , Christopher Pal

Reinforcement learning, mathematically described by Markov Decision Problems, may be approached either through dynamic programming or policy search. Actor-critic algorithms combine the merits of both approaches by alternating between steps…

Machine Learning · Computer Science 2023-01-31 Harshat Kumar , Alec Koppel , Alejandro Ribeiro

Learning a near optimal policy in a partially observable system remains an elusive challenge in contemporary reinforcement learning. In this work, we consider episodic reinforcement learning in a reward-mixing Markov decision process (MDP).…

Machine Learning · Computer Science 2022-02-01 Jeongyeol Kwon , Yonathan Efroni , Constantine Caramanis , Shie Mannor

Cooperative multi-agent reinforcement learning (MARL) aims to coordinate multiple agents to achieve a common goal. A key challenge in MARL is credit assignment, which involves assessing each agent's contribution to the shared reward. Given…

Artificial Intelligence · Computer Science 2025-08-12 Xutong Zhao , Yaqi Xie

This paper investigates infinite-horizon average reward Constrained Markov Decision Processes (CMDPs) with general parametrization. We propose a Primal-Dual Natural Actor-Critic algorithm that adeptly manages constraints while ensuring a…

Machine Learning · Computer Science 2025-12-11 Yang Xu , Swetha Ganesh , Washim Uddin Mondal , Qinbo Bai , Vaneet Aggarwal

We analyze the global convergence of the single-timescale actor-critic (AC) algorithm for the infinite-horizon discounted Markov Decision Processes (MDPs) with finite state spaces. To this end, we introduce an elegant analytical framework…

Machine Learning · Computer Science 2025-06-05 Navdeep Kumar , Priyank Agrawal , Giorgia Ramponi , Kfir Yehuda Levy , Shie Mannor

In order to model risk aversion in reinforcement learning, an emerging line of research adapts familiar algorithms to optimize coherent risk functionals, a class that includes conditional value-at-risk (CVaR). Because optimizing the…

Machine Learning · Computer Science 2021-03-09 Audrey Huang , Liu Leqi , Zachary C. Lipton , Kamyar Azizzadenesheli
‹ Prev 1 2 3 10 Next ›