English
Related papers

Related papers: A Finite-Sample Analysis of an Actor-Critic Algori…

200 papers

We discuss the approximation of the value function for infinite-horizon discounted Markov Reward Processes (MRP) with nonlinear functions trained with the Temporal-Difference (TD) learning algorithm. We first consider this problem under a…

Machine Learning · Computer Science 2024-02-05 Andrea Agazzi , Jianfeng Lu

In this paper, we study the finite-sample statistical rates of distributional temporal difference (TD) learning with linear function approximation. The purpose of distributional TD learning is to estimate the return distribution of a…

Machine Learning · Statistics 2025-11-18 Kaicheng Jin , Yang Peng , Jiansheng Yang , Zhihua Zhang

We address the issue of estimation bias in deep reinforcement learning (DRL) by introducing solution mechanisms that include a new, twin TD-regularized actor-critic (TDR) method. It aims at reducing both over and under-estimation errors.…

Machine Learning · Computer Science 2023-11-08 Junmin Zhong , Ruofan Wu , Jennie Si

We present a mean-variance policy iteration (MVPI) framework for risk-averse control in a discounted infinite horizon MDP optimizing the variance of a per-step reward random variable. MVPI enjoys great flexibility in that any policy…

Machine Learning · Computer Science 2022-04-08 Shangtong Zhang , Bo Liu , Shimon Whiteson

We present an actor-critic framework for MDPs where the objective is the variance-adjusted expected return. Our critic uses linear function approximation, and we extend the concept of compatible features to the variance-adjusted setting. We…

Machine Learning · Statistics 2013-10-15 Aviv Tamar , Shie Mannor

Reinforcement learning (RL) typically models the interaction between the agent and environment as a Markov decision process (MDP), where the rewards that guide the agent's behavior are always observable. However, in many real-world…

Artificial Intelligence · Computer Science 2025-05-15 Montaser Mohammedalamen , Michael Bowling

The average reward is a fundamental performance metric in reinforcement learning (RL) focusing on the long-run performance of an agent. Differential temporal difference (TD) learning algorithms are a major advance for average reward RL as…

Machine Learning · Computer Science 2026-02-19 Ethan Blaser , Jiuqi Wang , Shangtong Zhang

Stochastic and soft optimal policies resulting from entropy-regularized Markov decision processes (ER-MDP) are desirable for exploration and imitation learning applications. Motivated by the fact that such policies are sensitive with…

Machine Learning · Computer Science 2022-01-03 Tien Mai , Patrick Jaillet

This paper studies the policy mirror descent (PMD) method, which is a general policy optimization framework in reinforcement learning and can cover a wide range of policy gradient methods by specifying difference mirror maps. Existing…

Optimization and Control · Mathematics 2026-01-01 Wenye Li , Hongxu Chen , Jiacai Liu , Ke Wei

We study the setting of \emph{performative reinforcement learning} where the deployed policy affects both the reward, and the transition of the underlying Markov decision process. Prior work~\parencite{MTR23} has addressed this problem…

Machine Learning · Computer Science 2025-03-18 Debmalya Mandal , Goran Radanovic

Recent successful deep reinforcement learning algorithms, such as Trust Region Policy Optimization (TRPO) or Proximal Policy Optimization (PPO), are fundamentally variations of conservative policy iteration (CPI). These algorithms iterate…

Machine Learning · Computer Science 2020-01-27 Erinc Merdivan , Sten Hanke , Matthieu Geist

This paper investigates value function approximation in the context of zero-sum Markov games, which can be viewed as a generalization of the Markov decision process (MDP) framework to the two-agent case. We generalize error bounds from MDPs…

Artificial Intelligence · Computer Science 2013-01-07 Michail Lagoudakis , Ron Parr

We develop a stochastic approximation-type algorithm to solve finite state/action, infinite-horizon, risk-aware Markov decision processes. Our algorithm has two loops. The inner loop computes the risk by solving a stochastic saddle-point…

Optimization and Control · Mathematics 2019-12-05 Wenjie Huang , William B. Haskell

We study reward-free reinforcement learning (RL) with linear function approximation, where the agent works in two phases: (1) in the exploration phase, the agent interacts with the environment but cannot access the reward; and (2) in the…

Machine Learning · Computer Science 2024-02-15 Junkai Zhang , Weitong Zhang , Quanquan Gu

In this paper, we study the problem of reinforcement learning in multi-agent systems where communication among agents is limited. We develop a decentralized actor-critic learning framework in which each agent performs several local updates…

Machine Learning · Computer Science 2025-10-23 Xiaoxing Ren , Nicola Bastianello , Thomas Parisini , Andreas A. Malikopoulos

This study investigates the mean-variance (MV) trade-off in reinforcement learning (RL), an instance of the sequential decision-making under uncertainty. Our objective is to obtain MV-efficient policies whose means and variances are located…

Machine Learning · Computer Science 2024-11-14 Masahiro Kato , Kei Nakagawa , Kenshi Abe , Tetsuro Morimura , Kentaro Baba

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

In this paper, we consider the problem of deploying a robot from a specification given as a temporal logic statement about some properties satisfied by the regions of a large, partitioned environment. We assume that the robot has noisy…

Robotics · Computer Science 2012-02-24 Xu Chu Ding , Jing Wang , Morteza Lahijanian , Ioannis Ch. Paschalidis , Calin A. Belta

We consider controller synthesis for stochastic and partially unknown environments in which safety is essential. Specifically, we abstract the problem as a Markov decision process in which the expected performance is measured using a cost…

Software Engineering · Computer Science 2015-10-21 Sebastian Junges , Nils Jansen , Christian Dehnert , Ufuk Topcu , Joost-Pieter Katoen

We study policy gradient for mean-field control in continuous time in a reinforcement learning setting. By considering randomised policies with entropy regularisation, we derive a gradient expectation representation of the value function,…

Machine Learning · Statistics 2023-03-14 Noufel Frikha , Maximilien Germain , Mathieu Laurière , Huyên Pham , Xuanye Song