English
Related papers

Related papers: Variance-Constrained Actor-Critic Algorithms for D…

200 papers

Risk-bounded motion planning is an important yet difficult problem for safety-critical tasks. While existing mathematical programming methods offer theoretical guarantees in the context of constrained Markov decision processes, they either…

Machine Learning · Computer Science 2021-08-05 Xin Huang , Meng Feng , Ashkan Jasour , Guy Rosman , Brian Williams

Having a perfect model to compute the optimal policy is often infeasible in reinforcement learning. It is important in high-stakes domains to quantify and manage risk induced by model uncertainties. Entropic risk measure is an exponential…

Machine Learning · Computer Science 2020-06-23 Reazul Hasan Russel , Bahram Behzadian , Marek Petrik

We consider large-scale Markov decision processes (MDPs) with a risk measure of variability in cost, under the risk-aware MDPs paradigm. Previous studies showed that risk-aware MDPs, based on a minimax approach to handling risk, can be…

Systems and Control · Computer Science 2017-05-17 Pengqian Yu , William B. Haskell , Huan Xu

This note describes sufficient conditions under which total-cost and average-cost Markov decision processes (MDPs) with general state and action spaces, and with weakly continuous transition probabilities, can be reduced to discounted MDPs.…

Optimization and Control · Mathematics 2017-11-21 Eugene A. Feinberg , Jefferson Huang

We present a non-asymptotic convergence analysis of $Q$-learning and actor-critic algorithms for robust average-reward Markov Decision Processes (MDPs) under contamination, total-variation (TV) distance, and Wasserstein uncertainty sets. A…

Machine Learning · Computer Science 2025-12-11 Yang Xu , Swetha Ganesh , Vaneet Aggarwal

We study risk-sensitive RL where the goal is learn a history-dependent policy that optimizes some risk measure of cumulative rewards. We consider a family of risks called the optimized certainty equivalents (OCE), which captures important…

Machine Learning · Computer Science 2025-03-03 Kaiwen Wang , Dawen Liang , Nathan Kallus , Wen Sun

We consider a constrained Markov Decision Problem (CMDP) where the goal of an agent is to maximize the expected discounted sum of rewards over an infinite horizon while ensuring that the expected discounted sum of costs exceeds a certain…

Machine Learning · Computer Science 2024-11-01 Washim Uddin Mondal , Vaneet Aggarwal

CVaR (Conditional Value at Risk) is a risk metric widely used in finance. However, dynamically optimizing CVaR is difficult since it is not a standard Markov decision process (MDP) and the principle of dynamic programming fails. In this…

Optimization and Control · Mathematics 2022-10-18 Li Xia , Peter W. Glynn

Markov decision process (MDP) is a decision making framework where a decision maker is interested in maximizing the expected discounted value of a stream of rewards received at future stages at various states which are visited according to…

Optimization and Control · Mathematics 2022-12-19 Hoang Nam Nguyen , Abdel Lisser , Vikas Vikram Singh

This paper studies the optimization of Markov decision processes (MDPs) from a risk-seeking perspective, where the risk is measured by conditional value-at-risk (CVaR). The objective is to find a policy that maximizes the long-run CVaR of…

Optimization and Control · Mathematics 2023-12-05 Li Xia , Zhihui Yu , Peter W. Glynn

The average reward criterion is relatively less studied as most existing works in the Reinforcement Learning literature consider the discounted reward criterion. There are few recent works that present on-policy average reward actor-critic…

Machine Learning · Computer Science 2023-07-20 Naman Saxena , Subhojyoti Khastigir , Shishir Kolathaya , Shalabh Bhatnagar

This paper studies a distributed policy gradient in collaborative multi-agent reinforcement learning (MARL), where agents over a communication network aim to find the optimal policy to maximize the average of all agents' local returns. Due…

Multiagent Systems · Computer Science 2022-12-06 Xiaoxiao Zhao , Jinlong Lei , Li Li , Jie Chen

We propose a distributionally robust return-risk model for Markov decision processes (MDPs) under risk and reward ambiguity. The proposed model optimizes the weighted average of mean and percentile performances, and it covers the…

Machine Learning · Computer Science 2023-01-05 Haolin Ruan , Zhi Chen , Chin Pang Ho

We consider the problem of constrained Markov Decision Process (CMDP) where an agent interacts with a unichain Markov Decision Process. At every interaction, the agent obtains a reward. Further, there are $K$ cost functions. The agent aims…

Machine Learning · Computer Science 2022-06-22 Mridul Agarwal , Qinbo Bai , Vaneet Aggarwal

This paper studies the problem of data collection for policy evaluation in Markov decision processes (MDPs). In policy evaluation, we are given a target policy and asked to estimate the expected cumulative reward it will obtain in an…

Machine Learning · Computer Science 2022-06-22 Subhojyoti Mukherjee , Josiah P. Hanna , Robert Nowak

Many popular practical reinforcement learning (RL) algorithms employ evolving reward functions-through techniques such as reward shaping, entropy regularization, or curriculum learning-yet their theoretical foundations remain…

Machine Learning · Computer Science 2025-10-15 Rui Hu , Yu Chen , Longbo Huang

Controlled discrete time Markov processes are studied first with long run general discounting functional. It is shown that optimal strategies for average reward per unit time problem are also optimal for average generally discounting…

Optimization and Control · Mathematics 2023-06-27 Łukasz Stettner

We propose an actor-critic framework to solve the time-continuous stochastic optimal control problem. A least square temporal difference method is applied to compute the value function for the critic. The policy gradient method is…

Optimization and Control · Mathematics 2025-01-27 Mo Zhou , Jianfeng Lu

In classical Markov Decision Processes (MDPs), action costs and transition probabilities are assumed to be known, although an accurate estimation of these parameters is often not possible in practice. This study addresses MDPs under cost…

Optimization and Control · Mathematics 2019-06-24 Merve Merakli , Simge Kucukyavuz

Policy gradient algorithms have proven to be successful in diverse decision making and control tasks. However, these methods suffer from high sample complexity and instability issues. In this paper, we address these challenges by providing…

Machine Learning · Computer Science 2021-03-17 Yannis Flet-Berliac , Reda Ouhamma , Odalric-Ambrym Maillard , Philippe Preux