• Home
  • Search
  • Multi-agent Adaptive Dynamic Programming
  • Cite Icon1
  • https://doi.org/10.1007/10720076_52Copy DOI Icon

Multi-agent Adaptive Dynamic Programming

  • Jan 1, 2000
  • Snehasis Mukhopadhyay +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Dynamic programming offers an exact, general solution method for completely known sequential decision problems, formulated as Markov Decision Processes (MDP), with a finite number of states. Recently, there has been a great amount of interest in the adaptive version of the problem, where the task to be solved is not completely known a priori. In such a case, an agent has to acquire the necessary knowledge through learning, while simultaneously solving the optimal control or decision problem. A large variety of algorithms, variously known as Adaptive Dynamic Programming (ADP) or Reinforcement Learning (RL), has been proposed in the literature. However, almost invariably such algorithms suffer from slow convergence in terms of the number of experiments needed. In this paper we investigate how the learning speed can be considerably improved by exploiting and combining knowledge accumulated by multiple agents. These agents operate in the same task environment but follow possibly different trajectories. We discuss methods of combining the knowledge structures associated with the multiple agents and different strategies (with varying overheads) for knowledge communication between agents. Results of simulation experiments are also presented to indicate that combining multiple learning agents is a promising direction to improve learning speed. The method also performs significantly better than some of the fastest MDP learning algorithms such as the prioritized sweeping.

Similar Papers
  • Research Article
  • Citations4

Informed Sampling-Based Motion Planning for Manipulating Multiple Micro Agents Using Global External Electric Fields

  • Jul 01, 2022
  • IEEE Transactions on Automation Science and Engineering
  • Xilin Li +3
  • Book Chapter
  • Citations17

Solving Markov Decision Processes via Simulation

  • Sep 18, 2014
  • Abhijit Gosavi
  • Conference Article

Multiple Agents Interacting via Probability Flows on Factor Graphs

  • Jan 01, 2023
  • AHFE international
  • Francesco Palmieri +4
  • Conference Article
  • Citations6

Deep Reinforcement Learning for Multiple Agents in a Decentralized Architecture: A Case Study in the Telecommunication Domain

  • Mar 01, 2023
  • Hongyi Zhang +5
  • Research Article
  • Citations38

A clustering-based graph Laplacian framework for value function approximation in reinforcement learning.

  • Apr 25, 2014
  • IEEE transactions on cybernetics
  • Xin Xu +3
  • Research Article
  • Citations13

Reinforcement Learning for Clinical Applications.

  • Feb 08, 2023
  • Clinical Journal of the American Society of Nephrology
  • Kia Khezeli +5
  • Research Article
  • Citations5

Dual-Reward Reinforcement Learning with Intrinsic Exploration Mechanisms for Real-Time Reservoir Management

  • Jun 18, 2025
  • SPE Journal
  • Guojing Xin +7
  • Research Article
  • Citations9

심층 결정론적 정책 경사법을 이용한 선박 충돌 회피 경로 결정

  • Feb 20, 2019
  • Journal of the Society of Naval Architects of Korea
  • Dong-Ham Kim +3
  • Book Chapter
  • Citations4

Solving F $$^3$$ MDPs: Collaborative Multiagent Markov Decision Processes with Factored Transitions, Rewards and Stochastic Policies

  • Jan 01, 2015
  • Julia Radoszycki +2
  • Conference Article
  • Citations111

Learning and adaptivity in interactive recommender systems

  • Aug 19, 2007
  • Tariq Mahmood +1
  • Research Article
  • Citations6

Reinforcement Learning with Temporal Logic Constraints

  • Jan 01, 2020
  • IFAC-PapersOnLine
  • Bengt Lennartson +1
  • Research Article
  • Citations26

Probably Approximately Correct (PAC) exploration in reinforcement learning

  • Jan 01, 2007
  • Rutgers University Community Repository (Rutgers University)
  • Alexander L Strehl
  • Dissertation

Decision-making with cooperative multi-agent reinforcement learning

  • Jan 01, 2025
  • Jing Sun
  • Components
  • Citations7

Reward-predictive representations generalize across tasks in reinforcement learning

  • Oct 15, 2020
  • Lucas Lehnert +3
  • Conference Article
  • Citations2

Q-ac: multiagent reinforcement learning with perception-conversion action

  • Nov 10, 2003
  • R Sun +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.