Approximated multi-agent fitted Q iteration
From MaRDI portal
Abstract: We formulate an efficient approximation for multi-agent batch reinforcement learning, the approximated multi-agent fitted Q iteration (AMAFQI). We present a detailed derivation of our approach. We propose an iterative policy search and show that it yields a greedy policy with respect to multiple approximations of the centralized, learned Q-function. In each iteration and policy evaluation, AMAFQI requires a number of computations that scales linearly with the number of agents whereas the analogous number of computations increase exponentially for the fitted Q iteration (FQI), a commonly used approaches in batch reinforcement learning. This property of AMAFQI is fundamental for the design of a tractable multi-agent approach. We evaluate the performance of AMAFQI and compare it to FQI in numerical simulations. The simulations illustrate the significant computation time reduction when using AMAFQI instead of FQI in multi-agent problems and corroborate the similar performance of both approaches.
Recommendations
- Cooperative learning with joint state value approximation for multi-agent systems
- Distributed policy evaluation via inexact ADMM in multi-agent reinforcement learning
- Scalable Reinforcement Learning for Multiagent Networked Systems
- A new Q learning algorithm for multi-agent systems
- Learning Near-Optimal Policies with Bellman-Residual Minimization Based Fitted Policy Iteration and a Single Sample Path
Cites work
- \({\mathcal Q}\)-learning
- A concise introduction to multiagent systems and distributed artificial intelligence
- An introduction to statistical learning. With applications in R
- Extremely randomized trees
- scientific article; zbMATH DE number 5957269 (Why is no real title available?)
- scientific article; zbMATH DE number 3860199 (Why is no real title available?)
- scientific article; zbMATH DE number 3281211 (Why is no real title available?)
- If multi-agent learning is the answer, what is the question?
- Kernel-based reinforcement learning
- Kernel-based reinforcement learning in average-cost problems
- Multi-agent reinforcement learning: a selective overview of theories and algorithms
- Multidimensional binary search trees used for associative searching
- Policy evaluation with temporal differences: a survey and comparison
- Reinforcement learning. An introduction
Cited in
(3)
This page was built for publication: Approximated multi-agent fitted Q iteration
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6174070)
