English
Related papers

Related papers: Data-Driven Knowledge Transfer in Batch $Q^*$ Lear…

200 papers

Markov Decision Processes (MDPs) have been used to formulate many decision-making problems in science and engineering. The objective is to synthesize the best decision (action selection) policies to maximize expected rewards (or minimize…

Optimization and Control · Mathematics 2015-07-07 Mahmoud El Chamie , Behcet Acikmese

We study meta-learning in Markov Decision Processes (MDP) with linear transition models in the undiscounted episodic setting. Under a task sharedness metric based on model proximity we study task families characterized by a distribution…

Machine Learning · Computer Science 2022-01-24 Robert Müller , Aldo Pacchiano

We present an approach to reduce the communication of information needed on a Distributed Q-Learning system inspired by Event Triggered Control (ETC) techniques. We consider a baseline scenario of a distributed Q-learning problem on a…

Artificial Intelligence · Computer Science 2021-12-07 Daniel Jarne Ornia , Manuel Mazo

In up-to-date machine learning (ML) applications on cloud or edge computing platforms, batching is an important technique for providing efficient and economical services at scale. In particular, parallel computing resources on the…

Machine Learning · Computer Science 2023-09-04 Yaodan Xu , Jingzhou Sun , Sheng Zhou , Zhisheng Niu

We propose a new simple and natural algorithm for learning the optimal Q-value function of a discounted-cost Markov Decision Process (MDP) when the transition kernels are unknown. Unlike the classical learning algorithms for MDPs, such as…

Optimization and Control · Mathematics 2019-01-31 Dileep Kalathil , Vivek S. Borkar , Rahul Jain

Reinforcement learning studies how an agent should interact with an environment to maximize its cumulative reward. A standard way to study this question abstractly is to ask how many samples an agent needs from the environment to learn an…

Quantum Physics · Physics 2021-12-21 Daochen Wang , Aarthi Sundaram , Robin Kothari , Ashish Kapoor , Martin Roetteler

This paper studies a finite-horizon Markov decision problem with information-theoretic constraints, where the goal is to minimize directed information from the controlled source process to the control process, subject to stage-wise cost…

Systems and Control · Electrical Eng. & Systems 2025-09-04 Zixuan He , Charalambos D. Charalambous , Photios A. Stavrou

This paper studies the statistical theory of batch data reinforcement learning with function approximation. Consider the off-policy evaluation problem, which is to estimate the cumulative value of a new target policy from logged history…

Machine Learning · Computer Science 2020-02-25 Yaqi Duan , Mengdi Wang

In this paper, we consider reinforcement learning of Markov Decision Processes (MDP) with peak constraints, where an agent chooses a policy to optimize an objective and at the same time satisfy additional constraints. The agent has to take…

Optimization and Control · Mathematics 2019-12-09 Ather Gattami

Many consumer decisions are repeated choices under uncertainty. Standard models capture these decisions using Bayesian learning and dynamic programming: consumers update beliefs from feedback and use those beliefs to guide future choices.…

Machine Learning · Computer Science 2026-05-19 Mehrzad Khosravi , Max Kleiman-Weiner , Hema Yoganarasimhan

Transferring knowledge from large source datasets is an effective way to fine-tune the deep neural networks of the target task with a small sample size. A great number of algorithms have been proposed to facilitate deep transfer learning,…

Machine Learning · Computer Science 2020-07-21 Xingjian Li , Haoyi Xiong , Haozhe An , Chengzhong Xu , Dejing Dou

Reinforcement learning (RL) is a classical tool to solve network control or policy optimization problems in unknown environments. The original Q-learning suffers from performance and complexity challenges across very large networks. Herein,…

Machine Learning · Computer Science 2024-09-02 Talha Bozkus , Urbashi Mitra

Asynchronous Q-learning aims to learn the optimal action-value function (or Q-function) of a Markov decision process (MDP), based on a single trajectory of Markovian samples induced by a behavior policy. Focusing on a $\gamma$-discounted…

Machine Learning · Computer Science 2022-09-13 Gen Li , Yuting Wei , Yuejie Chi , Yuantao Gu , Yuxin Chen

Markov decision processes (MDPs) are used to model a wide variety of applications ranging from game playing over robotics to finance. Their optimal policy typically maximizes the expected sum of rewards given at each step of the decision…

Machine Learning · Computer Science 2025-05-26 Maximilian Nägele , Jan Olle , Thomas Fösel , Remmy Zen , Florian Marquardt

General purpose intelligent learning agents cycle through (complex,non-MDP) sequences of observations, actions, and rewards. On the other hand, reinforcement learning is well-developed for small finite state Markov Decision Processes…

Artificial Intelligence · Computer Science 2009-12-30 Marcus Hutter

In this work, we focus on the problem of safe policy transfer in reinforcement learning: we seek to leverage existing policies when learning a new task with specified constraints. This problem is important for safety-critical applications…

Machine Learning · Computer Science 2022-11-11 Zeyu Feng , Bowen Zhang , Jianxin Bi , Harold Soh

Centralized training with decentralized execution has become an important paradigm in multi-agent learning. Though practical, current methods rely on restrictive assumptions to decompose the centralized value function across agents for…

Machine Learning · Computer Science 2020-06-11 Yaodong Yang , Ying Wen , Liheng Chen , Jun Wang , Kun Shao , David Mguni , Weinan Zhang

Decentralized collaborative learning under data heterogeneity and privacy constraints has rapidly advanced. However, existing solutions like federated learning, ensembles, and transfer learning, often fail to adequately serve the unique…

Machine Learning · Computer Science 2025-04-15 Norah Alballa , Wenxuan Zhang , Ziquan Liu , Ahmed M. Abdelmoniem , Mohamed Elhoseiny , Marco Canini

We present algorithms to effectively represent a set of Markov decision processes (MDPs), whose optimal policies have already been learned, by a smaller source subset for lifelong, policy-reuse-based transfer learning in reinforcement…

Artificial Intelligence · Computer Science 2016-05-03 M. M. Hassan Mahmud , Majd Hawasly , Benjamin Rosman , Subramanian Ramamoorthy

This paper introduces the QMDP-net, a neural network architecture for planning under partial observability. The QMDP-net combines the strengths of model-free learning and model-based planning. It is a recurrent policy network, but it…

Artificial Intelligence · Computer Science 2017-11-06 Peter Karkus , David Hsu , Wee Sun Lee