English
Related papers

Related papers: Finite-Time Error Analysis of Soft Q-Learning: Swi…

200 papers

Reinforcement learning algorithms are commonly analyzed (and designed) under the Markov assumption. This is unrealistic, as most environments encountered in practice are either partially observable, or require function approximation that…

Machine Learning · Computer Science 2026-05-28 Onno Eberhard , Claire Vernade , Michael Muehlebach

Reinforcement learning (RL) for exponential-utility optimization in discounted Markov decision processes (MDPs) lacks principled value-based algorithms. We address this gap in the fixed risk-aversion setting. Building on the Bellman-type…

Machine Learning · Computer Science 2026-05-11 Gugan Thoppe , L. A. Prashanth , Ankur Naskar , Sanjay Bhat

The exploration-exploitation dilemma has been a central challenge in reinforcement learning (RL) with complex model classes. In this paper, we propose a new algorithm, Monotonic Q-Learning with Upper Confidence Bound (MQL-UCB) for RL with…

Machine Learning · Computer Science 2025-10-06 Heyang Zhao , Jiafan He , Quanquan Gu

In Markov decision processes (MDPs), quantile risk measures such as Value-at-Risk are a standard metric for modeling RL agents' preferences for certain outcomes. This paper proposes a new Q-learning algorithm for quantile optimization in…

Machine Learning · Computer Science 2024-11-01 Jia Lin Hau , Erick Delage , Esther Derman , Mohammad Ghavamzadeh , Marek Petrik

In this paper, we present an online reinforcement learning algorithm for constrained Markov decision processes with a safety constraint. Despite the necessary attention of the scientific community, considering stochastic stopping time, the…

Machine Learning · Computer Science 2024-03-26 Abhijit Mazumdar , Rafal Wisniewski , Manuela L. Bujorianu

We consider a prospect theoretic version of the classical Q-learning algorithm for discounted reward Markov decision processes, wherein the controller perceives a distorted and noisy future reward, modeled by a nonlinearity that accentuates…

Systems and Control · Electrical Eng. & Systems 2021-09-02 Vivek S. Borkar , Siddharth Chandak

The paper considers a class of multi-agent Markov decision processes (MDPs), in which the network agents respond differently (as manifested by the instantaneous one-stage random costs) to a global controlled state and the control actions of…

Machine Learning · Statistics 2015-06-04 Soummya Kar , Jose' M. F. Moura , H. Vincent Poor

The goal of robust reinforcement learning (RL) is to learn a policy that is robust against the uncertainty in model parameters. Parameter uncertainty commonly occurs in many real-world RL applications due to simulator modeling errors,…

Machine Learning · Computer Science 2022-10-19 Kishan Panaganti , Zaiyan Xu , Dileep Kalathil , Mohammad Ghavamzadeh

Self-imitation learning motivated by lower-bound Q-learning is a novel and effective approach for off-policy learning. In this work, we propose a n-step lower bound which generalizes the original return-based lower-bound Q-learning, and…

Machine Learning · Computer Science 2021-02-16 Yunhao Tang

In this paper, we present a novel algorithm named synchronous integral Q-learning, which is based on synchronous policy iteration, to solve the continuous-time infinite horizon optimal control problems of input-affine system dynamics. The…

Systems and Control · Electrical Eng. & Systems 2021-05-20 Lei Guo , Han Zhao

Inspired by the \emph{Well-initialized Lottery Ticket Hypothesis (WLTH)}, we introduce Soft-Transformer (Soft-TF), a parameter-efficient framework for continual learning that leverages soft, real-valued subnetworks over a frozen pre-trained…

Machine Learning · Computer Science 2026-04-29 Haeyong Kang , Chang D. Yoo

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

In this paper, we place deep Q-learning into a control-oriented perspective and study its learning dynamics with well-established techniques from robust control. We formulate an uncertain linear time-invariant model by means of the neural…

Machine Learning · Computer Science 2022-11-08 Balazs Varga , Balazs Kulcsar , Morteza Haghir Chehreghani

For the identification of switched systems with a measured switching signal, this work aims to analyze the effect of switching strategies on the estimation error. The data for identification is assumed to be collected from globally…

Systems and Control · Electrical Eng. & Systems 2022-07-26 Shengling Shi , Othmane Mazhar , Bart De Schutter

We introduce Extreme Quantum Cognition Machines, a class of quantum learning architectures for deliberative decision making that is tolerant to noisy and contradictory training data. Inspired by the quantum cognition paradigm, Extreme…

Quantum Physics · Physics 2026-05-15 Francesco Romeo , Jacopo Settino

This work uses the entropy-regularised relaxed stochastic control perspective as a principled framework for designing reinforcement learning (RL) algorithms. Herein agent interacts with the environment by generating noisy controls…

Machine Learning · Computer Science 2023-09-18 Lukasz Szpruch , Tanut Treetanthiploet , Yufei Zhang

The article describes the use of deep Q-learning models in the problems of sales time series analytics. In contrast to supervised machine learning which is a kind of passive learning using historical data, Q-learning is a kind of active…

Machine Learning · Computer Science 2022-01-07 Bohdan M. Pavlyshenko

Multi-Agent Reinforcement Learning involves agents that learn together in a shared environment, leading to emergent dynamics sensitive to initial conditions and parameter variations. A Dynamical Systems approach, which studies the evolution…

Multiagent Systems · Computer Science 2025-01-03 David Goll , Jobst Heitzig , Wolfram Barfuss

Stability issues with reinforcement learning methods persist. To better understand some of these stability and convergence issues involving deep reinforcement learning methods, we examine a simple linear quadratic example. We interpret the…

Machine Learning · Computer Science 2024-06-03 Lingyi Yang

We present the convergence rates of synchronous and asynchronous Q-learning for average-reward Markov decision processes, where the absence of contraction poses a fundamental challenge. Existing non-asymptotic results overcome this…

Machine Learning · Computer Science 2026-01-30 Zijun Chen , Zaiwei Chen , Nian Si , Shengbo Wang