Multi-agent reinforcement learning: a selective overview of theories and algorithms (Q2094040)

scientific article; zbMATH DE number 7608712

Language	Label	Description	Also known as
default for all languages	No label defined
English	Multi-agent reinforcement learning: a selective overview of theories and algorithms	scientific article; zbMATH DE number 7608712

Statements

instance of

scholarly article

0 references

title

Multi-agent reinforcement learning: a selective overview of theories and algorithms (English)

0 references

0 references

0 references

0 references

28 October 2022

0 references

full work available at URL

https://arxiv.org/abs/1911.10635

0 references

describes a project that uses

0 references

0 references

0 references

0 references

0 references

MaRDI publication profile

0 references

cites work

Superhuman AI for multiplayer poker

0 references

Distributed learning and cooperative control for multi-agent systems

0 references

Dynamic Potential Games With Constraints: Fundamentals and Applications in Communications

0 references

A concise introduction to decentralized POMDPs

0 references

Decentralized Q-Learning for Stochastic Teams and Games

0 references

State of the Art—A Survey of Partially Observable Markov Decision Processes: Theory, Models, and Algorithms

0 references

Dynamic programming and optimal control. Vol. 1.

0 references

${\mathcal Q}$-learning

0 references

Convergence results for single-step on-policy reinforcement-learning algorithms

0 references

An Adaptive Sampling Algorithm for Solving Markov Decision Processes

0 references

Sample mean based index policies by <i>O</i>(log <i>n</i>) regret for the multi-armed bandit problem

0 references

Finite-time analysis of the multiarmed bandit problem

0 references

Reinforcement learning. An introduction

0 references

Policy evaluation with temporal differences: a survey and comparison

0 references

Simple statistical gradient-following algorithms for connectionist reinforcement learning

0 references

Q4533362

0 references

OnActor-Critic Algorithms

0 references

Natural actor-critic algorithms

0 references

Global convergence of policy gradient methods to (almost) locally optimal policies

0 references

Stochastic Games

0 references

Q4226167

0 references

Q4382287

0 references

Decomposition of dynamic team decision problems

0 references

Discrete-time stochastic control and dynamic potential games. The Euler-equation approach

0 references

${{\cal Q} {\cal D}}$-Learning: A Collaborative Distributed Strategy for Multi-Agent Reinforcement Learning Through ${\rm Consensus} + {\rm Innovations}$

0 references

Optimal stochastic linear systems with exponential performance criteria and their relation to deterministic differential games

0 references

$H^ \infty$-optimal control and related minimax design problems. A dynamic game approach.

0 references

10.1162/1532443041827880

0 references

The Complexity of Decentralized Control of Markov Decision Processes

0 references

A course in game theory.

0 references

Multiagent Systems

0 references

The complexity of two-person zero-sum games in extensive form

0 references

Q5817864

0 references

AWESOME: a general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents

0 references

If multi-agent learning is the answer, what is the question?

0 references

Multiagent learning using a variable learning rate

0 references

Learning, regret minimization, and equilibria

0 references

Q4552708

0 references

Monotonic value function factorisation for deep multi-agent reinforcement learning

0 references

Optimal Decentralized Control of Coupled Subsystems With Control Sharing

0 references

Distributed Policy Evaluation Under Multiple Behavior Strategies

0 references

Finite-time performance of distributed temporal-difference learning with linear function approximation

0 references

The Evolution of Conventions

0 references

Potential games

0 references

Handbook of dynamic game theory. In 2 volumes

0 references

Large population stochastic dynamic games: closed-loop McKean-Vlasov systems and the Nash certainty equivalence principle

0 references

Mean field games

0 references

Mean field games and mean field type control theory

0 references

Risk-Sensitive Mean-Field Games

0 references

Stochastic networked control systems. Stabilization and optimization under information constraints

0 references

Distributed learning of average belief over networks using sequential observations

0 references

Distributed Subgradient Methods for Multi-Agent Optimization

0 references

Cooperative Convex Optimization in Networked Systems: Augmented Lagrangian Algorithms With Directed Gossip Communication

0 references

Diffusion Strategies Outperform Consensus Strategies for Distributed Estimation Over Adaptive Networks

0 references

Expected policy gradients for reinforcement learning

0 references

An emphatic approach to the problem of off-policy temporal-difference learning

0 references

A Distributed Actor-Critic Algorithm and Applications to Mobile Sensor Network Coordination Problems

0 references

Stochastic Proximal Gradient Consensus Over Random Networks

0 references

Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs

0 references

Performance Bounds in $L_p$‐norm for Approximate Value Iteration

0 references

Finite-time bounds for fitted value iteration

0 references

Learning Near-Optimal Policies with Bellman-Residual Minimization Based Fitted Policy Iteration and a Single Sample Path

0 references

Harnessing Smoothness to Accelerate Distributed Optimization

0 references

Minimizing finite sums with the stochastic average gradient

0 references

Reinforcement learning with replacing eligibility traces

0 references

Distributed Stochastic Approximation: Weak Convergence and Network Design

0 references

Q3624177

0 references

Optimally solving Dec-POMDPs as continuous-state MDPs

0 references

Decentralized Stochastic Control with Partial History Sharing: A Common Information Approach

0 references

Q4027186

0 references

The complexity of computing a Nash equilibrium

0 references

Q3433855

0 references

On Nonterminating Stochastic Games

0 references

Discounted Markov games: Generalized policy iteration method

0 references

Algorithms for discounted stochastic games

0 references

Strategy iteration is strongly polynomial for 2-player turn-based stochastic games with a constant discount factor

0 references

Model-free $Q$-learning designs for linear discrete-time zero-sum games with application to $H^\infty$ control

0 references

Regularized policy iteration with nonparametric function spaces

0 references

Near-optimal regret bounds for reinforcement learning

0 references

Fast algorithms for finding randomized strategies in game trees

0 references

Efficient computation of behavior strategies

0 references

Efficient computation of equilibria for extensive two-person games

0 references

Q4506458

0 references

Q3245635

0 references

Q5808755

0 references

An iterative method of solving a game

0 references

Stochastic Approximations and Differential Inclusions

0 references

A general class of adaptive strategies

0 references

Belief affirming in learning processes

0 references

No-regret dynamics and fictitious play

0 references

Q4421713

0 references

Consistency and cautious fictitious play

0 references

On the Global Convergence of Stochastic Fictitious Play

0 references

Generalised weakened fictitious play

0 references

Consistency of vanishingly smooth fictitious play

0 references

Sampled fictitious play is Hannan consistent

0 references

Q3093261

0 references

Stochastic approximation. A dynamical systems viewpoint.

0 references

Prediction, Learning, and Games

0 references

The Nonstochastic Multiarmed Bandit Problem

0 references

The weighted majority algorithm

0 references

Adaptive game playing using multiplicative weights

0 references

A Simple Adaptive Procedure Leading to Correlated Equilibrium

0 references

Revisiting CFR$^+$ and alternating updates

0 references

Analysis of Hannan consistent selection for Monte Carlo tree search in simultaneous move games

0 references

Q5381139

0 references

Settling the complexity of computing two-player Nash equilibria

0 references

Subjectivity and correlation in randomized strategies

0 references

Markov-Nash equilibria in mean-field games with discounted cost

0 references

Approximate Nash equilibria in partially observed stochastic games with mean-field interactions

0 references

Discrete-time average-cost mean-field games on Polish spaces

0 references

Approximate Markov-Nash equilibria for discrete-time risk-sensitive mean-field games

0 references

Finite mean field games: fictitious play and convergence to a first order continuous mean field game

0 references

Value iteration algorithm for mean-field games

0 references

A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

0 references

The challenge of poker

0 references

Q5801632

0 references

DeepStack: expert-level artificial intelligence in heads-up no-limit poker

0 references

Superhuman AI for heads-up no-limit poker: Libratus beats top professionals

0 references

A near-optimal polynomial time algorithm for learning in certain classes of stochastic games

0 references

10.1162/153244303765208377

0 references

A comprehensive survey on safe reinforcement learning

0 references

Identifiers

DOI

10.1007/978-3-030-60990-0_12

0 references

Mathematics Subject Classification ID

0 references

0 references

0 references

Sitelinks

Mathematics(1 entry)

mardi Publication:2094040