Search Results for author: Michael Wooldridge

Found 17 papers, 4 papers with code

Multiagent Model-based Credit Assignment for Continuous Control

no code implementations27 Dec 2021 Dongge Han, Chris Xiaoxuan Lu, Tomasz Michalak, Michael Wooldridge

By formulating robotic components as a system of decentralised agents, this work presents a decentralised multiagent reinforcement learning framework for continuous control.

Continuous Control reinforcement-learning

MDP Abstraction with Successor Features

no code implementations18 Oct 2021 Dongge Han, Michael Wooldridge, Sebastian Tschiatschek

This includes an algorithm for encoding and instantiation of abstract options across different environments, and a state abstraction mechanism based on the abstract options.

Rational Verification for Probabilistic Systems

no code implementations19 Jul 2021 Julian Gutierrez, Lewis Hammond, Anthony W. Lin, Muhammad Najib, Michael Wooldridge

Rational verification is the problem of determining which temporal logic properties will hold in a multi-agent system, under the assumption that agents in the system act rationally, by choosing strategies that collectively form a game-theoretic equilibrium.

Equilibrium Design for Concurrent Games

no code implementations18 Jun 2021 Julian Gutierrez, Muhammad Najib, Giuseppe Perelli, Michael Wooldridge

In particular, we consider system specifications given by LTL and GR(1) formulae, and show that implementing a mechanism to ensure that a given temporal logic property is satisfied on some/every Nash equilibrium of the game, whenever such a mechanism exists, can be done in PSPACE for LTL properties and in NP/$\Sigma^{P}_{2}$ for GR(1) specifications.

Equilibrium Refinements for Multi-Agent Influence Diagrams: Theory and Practice

1 code implementation9 Feb 2021 Lewis Hammond, James Fox, Tom Everitt, Alessandro Abate, Michael Wooldridge

Multi-agent influence diagrams (MAIDs) are a popular form of graphical model that, for certain classes of games, have been shown to offer key complexity and explainability advantages over traditional extensive form game (EFG) representations.

Multi-Agent Reinforcement Learning with Temporal Logic Specifications

1 code implementation1 Feb 2021 Lewis Hammond, Alessandro Abate, Julian Gutierrez, Michael Wooldridge

In this paper, we study the problem of learning to satisfy temporal logic specifications with a group of agents in an unknown environment, which may exhibit probabilistic behaviour.

Multi-agent Reinforcement Learning reinforcement-learning

Multi-Player Games with LDL Goals over Finite Traces

no code implementations13 Aug 2020 Julian Gutierrez, Giuseppe Perelli, Michael Wooldridge

Linear Dynamic Logic on finite traces LDLf is a powerful logic for reasoning about the behaviour of concurrent and multi-agent systems.

Equilibria for Games with Combined Qualitative and Quantitative Objectives

no code implementations13 Aug 2020 Julian Gutierrez, Aniello Murano, Giuseppe Perelli, Sasha Rubin, Thomas Steeples, Michael Wooldridge

The overall aim of our research is to develop techniques to reason about the equilibrium properties of multi-agent systems.

Automated Temporal Equilibrium Analysis: Verification and Synthesis of Multi-Player Games

1 code implementation13 Aug 2020 Julian Gutierrez, Muhammad Najib, Giuseppe Perelli, Michael Wooldridge

In the context of multi-agent systems, the rational verification problem is concerned with checking which temporal logic properties will hold in a system when its constituent agents are assumed to behave rationally and strategically in pursuit of individual objectives.

Replication Robust Payoff Allocation in Submodular Cooperative Games

no code implementations25 Jun 2020 Dongge Han, Michael Wooldridge, Alex Rogers, Olga Ohrimenko, Sebastian Tschiatschek

In this paper, we systematically study the replication manipulation in submodular games and investigate replication robustness, a metric that quantitatively measures the robustness of solution concepts against replication.

Multi-agent Hierarchical Reinforcement Learning with Dynamic Termination

no code implementations21 Oct 2019 Dongge Han, Wendelin Boehmer, Michael Wooldridge, Alex Rogers

We evaluate our model empirically on a set of multi-agent pursuit and taxi tasks, and show that our agents learn to adapt flexibly across scenarios that require different termination behaviours.

Hierarchical Reinforcement Learning reinforcement-learning

Manipulating a Learning Defender and Ways to Counteract

no code implementations NeurIPS 2019 Jiarui Gan, Qingyu Guo, Long Tran-Thanh, Bo An, Michael Wooldridge

We then apply a game-theoretic framework at a higher level to counteract such manipulation, in which the defender commits to a policy that specifies her strategy commitment according to the learned information.

Game-theoretic Network Centrality: A Review

no code implementations31 Dec 2017 Mateusz K. Tarkowski, Tomasz P. Michalak, Talal Rahwan, Michael Wooldridge

Game-theoretic centrality is a flexible and sophisticated approach to identify the most important nodes in a network.

Hiding Individuals and Communities in a Social Network

no code implementations1 Aug 2016 Marcin Waniek, Tomasz Michalak, Talal Rahwan, Michael Wooldridge

With this in mind, we ask the question: Can individuals or groups actively manage their connections to evade social network analysis tools?

Social and Information Networks Physics and Society 91D30 (Primary) 68T20 (Secondary) G.2.2; J.4

Boolean Hedonic Games

no code implementations23 Sep 2015 Haris Aziz, Paul Harrenstein, Jérôme Lang, Michael Wooldridge

The assumption of dichotomous preferences means that, additionally, each player's preference relation partitions the set of coalitions of which that player is a member into just two equivalence classes: satisfactory and unsatisfactory.

Reasoning About the Transfer of Control

no code implementations16 Jan 2014 Wiebe van der Hoek, Dirk Walther, Michael Wooldridge

The logical foundation of DCL-PC is CL-PC, a logic for reasoning about cooperation in which the abilities of agents and coalitions of agents stem from a distribution of atomic Boolean variables to individual agents -- the choices available to a coalition correspond to assignments to the variables the coalition controls.

A Linear Approximation Method for the Shapley Value

1 code implementation1 Sep 2008 S. Shaheen Fatima, Michael Wooldridge, Nicholas R. Jennings

This method has time complexity linear in the number of players, but has an approximation error that is, on average, lower than Owen's.

Cannot find the paper you are looking for? You can Submit a new open access paper.