English
Related papers

Related papers: An Actor-Critic Algorithm with Function Approximat…

200 papers

Policy gradient methods are widely used for control in reinforcement learning, particularly for the continuous action setting. There have been a host of theoretically sound algorithms proposed for the on-policy setting, due to the existence…

Machine Learning · Computer Science 2019-06-21 Ehsan Imani , Eric Graves , Martha White

The policy gradient theorem (Sutton et al., 2000) prescribes the usage of a cumulative discounted state distribution under the target policy to approximate the gradient. Most algorithms based on this theorem, in practice, break this…

Machine Learning · Computer Science 2022-07-08 Samuele Tosatto , Andrew Patterson , Martha White , A. Rupam Mahmood

In this paper, we consider discrete-time partially observed mean-field games with the risk-sensitive optimality criterion. We introduce risk-sensitivity behaviour for each agent via an exponential utility function. In the game model, each…

Systems and Control · Electrical Eng. & Systems 2022-11-11 Naci Saldi , Tamer Basar , Maxim Raginsky

We study Markov potential games under the infinite horizon average reward criterion. Most previous studies have been for discounted rewards. We prove that both algorithms based on independent policy gradient and independent natural policy…

Machine Learning · Computer Science 2024-03-12 Min Cheng , Ruida Zhou , P. R. Kumar , Chao Tian

While deep reinforcement learning has achieved tremendous successes in various applications, most existing works only focus on maximizing the expected value of total return and thus ignore its inherent stochasticity. Such stochasticity is…

Machine Learning · Computer Science 2023-09-19 Han Zhong , Xun Deng , Ethan X. Fang , Zhuoran Yang , Zhaoran Wang , Runze Li

We obtain weak rates for approximation of an integral functional of a Markov process by integral sums. An assumption on the process is formulated only in terms of its transition probability density, and, therefore, our approach is not…

Probability · Mathematics 2015-10-08 Iurii Ganychenko , Alexei Kulik

This note summarizes the optimization formulations used in the study of Markov decision processes. We consider both the discounted and undiscounted processes under the standard and the entropy-regularized settings. For each setting, we…

Optimization and Control · Mathematics 2020-12-18 Lexing Ying , Yuhua Zhu

We consider a piecewise deterministic Markov decision process, where the expected exponential utility of total (nonnegative) cost is to be minimized. The cost rate, transition rate and post-jump distributions are under control. The state…

Optimization and Control · Mathematics 2017-11-22 Xin Guo , Yi Zhang

We examine global non-asymptotic convergence properties of policy gradient methods for multi-agent reinforcement learning (RL) problems in Markov potential games (MPG). To learn a Nash equilibrium of an MPG in which the size of state space…

Machine Learning · Computer Science 2022-08-08 Dongsheng Ding , Chen-Yu Wei , Kaiqing Zhang , Mihailo R. Jovanović

In this paper we address the problem of decision making within a Markov decision process (MDP) framework where risk and modeling errors are taken into account. Our approach is to minimize a risk-sensitive conditional-value-at-risk (CVaR)…

Artificial Intelligence · Computer Science 2015-06-09 Yinlam Chow , Aviv Tamar , Shie Mannor , Marco Pavone

Actor-critic methods, a type of model-free Reinforcement Learning, have been successfully applied to challenging tasks in continuous control, often achieving state-of-the art performance. However, wide-scale adoption of these methods in…

Machine Learning · Statistics 2019-10-29 Kamil Ciosek , Quan Vuong , Robert Loftin , Katja Hofmann

We study policy gradient methods for reinforcement learning in non-Markovian decision processes (NMDPs), where observations and rewards depend on the entire interaction history. To handle this dependence, the agent maintains an internal…

Machine Learning · Computer Science 2026-05-12 Avik Kar , Siddharth Chandak , Rahul Singh , Soumitra Sinhahajari , Eric Moulines , Shalabh Bhatnagar , Nicholas Bambos

Markov Decision Processes are classically solved using Value Iteration and Policy Iteration algorithms. Recent interest in Reinforcement Learning has motivated the study of methods inspired by optimization, such as gradient ascent. Among…

Machine Learning · Computer Science 2021-05-05 Sajad Khodadadian , Prakirt Raj Jhunjhunwala , Sushil Mahavir Varma , Siva Theja Maguluri

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 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

We consider a Markov decision process subject to model uncertainty in a Bayesian framework, where we assume that the state process is observed but its law is unknown to the observer. In addition, while the state process and the controls are…

Optimization and Control · Mathematics 2022-06-22 Tomasz R. Bielecki , Igor Cialenco , Andrzej Ruszczyński

In this paper we propose several novel distributed gradient-based temporal difference algorithms for multi-agent off-policy learning of linear approximation of the value function in Markov decision processes with strict information…

Machine Learning · Computer Science 2021-04-20 Milos S. Stankovic , Marko Beko , Srdjan S. Stankovic

We develop a framework for convexifying a fairly general class of optimization problems. Under additional assumptions, we analyze the suboptimality of the solution to the convexified problem relative to the original nonconvex problem and…

Systems and Control · Computer Science 2014-06-04 Krishnamurthy Dvijotham , Maryam Fazel , Emanuel Todorov

Actor-critic (AC) is a powerful method for learning an optimal policy in reinforcement learning, where the critic uses algorithms, e.g., temporal difference (TD) learning with function approximation, to evaluate the current policy and the…

Machine Learning · Computer Science 2024-06-05 Yudan Wang , Yue Wang , Yi Zhou , Shaofeng Zou

A variety of theoretically-sound policy gradient algorithms exist for the on-policy setting due to the policy gradient theorem, which provides a simplified form for the gradient. The off-policy setting, however, has been less clear due to…

Machine Learning · Computer Science 2023-04-17 Eric Graves , Ehsan Imani , Raksha Kumaraswamy , Martha White