Influence-based Decision-making in Uncertain Environments

Informations projet

INFLUENCE

N° de convention de subvention: 758824

DOI

10.3030/758824

Projet clôturé

Date de signature de la CE 16 Novembre 2017

Date de début 1 Février 2018

Date de fin 31 Janvier 2023

Financé au titre de

• EXCELLENT SCIENCE - European Research Council (ERC)

Coût total

€ 1 475 560,00

Contribution de l’UE

€ 1 475 560,00

Coordonné par

TECHNISCHE UNIVERSITEIT DELFT
Netherlands

CORDIS fournit des liens vers les livrables publics et les publications des projets HORIZON.

Les liens vers les livrables et les publications des projets du 7e PC, ainsi que les liens vers certains types de résultats spécifiques tels que les jeux de données et les logiciels, sont récupérés dynamiquement sur OpenAIRE .

Publications

Conference proceedings (36)

Influence-Augmented Online Planning for Complex Environments

Auteurs: He, Jinke; Suau, Miguel; Oliehoek, Frans A.
Publié dans: Advances in Neural Information Processing Systems 33 (NeurIPS 2020), Numéro 33, 2020
Éditeur: Curran Associates, Inc.

Influence-Augmented Local Simulators: a Scalable Solution for Fast Deep RL in Large Networked Systems

Auteurs: Suau, Miguel; He, Jinke; Spaan, Matthijs T. J.; Oliehoek, Frans A.
Publié dans: Proceedings of the 39th International Conference on Machine Learning, Numéro PMLR 162, 2022, Page(s) 20604-20624
Éditeur: PMLR

A Cross-Field Review of State Abstraction for Markov Decision Processes.

Auteurs: Elena Congeduti, Frans A. Oliehoek
Publié dans: In Proceedings of the 34th Benelux Conference on Artificial Intelligence (BNAIC) and the 30th Belgian Dutch Conference on Machine Learning (Benelearn), 2022
Éditeur: BNAIC/Benelearn

Exploring the effects of conditioning Independent Q-Learners on the Sufficient Statistic for Dec-POMDPs

Auteurs: Alex Mandersloot, Frans A. Oliehoek, Aleksander Czechowski
Publié dans: Proceedings of the 32nd Benelux Conference on Artificial Intelligence (BNAIC) and the 29th Belgian Dutch Conference on Machine Learning (Benelearn), 2020
Éditeur: BNAIC/Benelearn

Constraint Propagation and Reverse Multi-Agent Learning

Auteurs: Aleksander Czechowski
Publié dans: AAAI Spring Symposium on Challenges and Opportunities for Multi-Agent Reinforcement Learning (COMARL), 2021
Éditeur: AAAI

Best-Response Bayesian Reinforcement Learning with Bayes-adaptive POMDPs for Centaurs

Auteurs: Celikok, Mustafa Mert; Frans A. Oliehoek; Samuel Kaski.
Publié dans: Proceedings of the Twenty-First International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2022, Page(s) 235-243
Éditeur: IFAAMAS

MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning

Auteurs: Van der Pol, Elise; Daniel E. Worrall; Herke Van Hoof; Frans A. Oliehoek; Max Welling.
Publié dans: Advances in Neural Information Processing Systems 33, 2020, Page(s) 4199–4210
Éditeur: Curran Associates, Inc.

Difference Rewards Policy Gradients

Auteurs: Jacopo Castellini; Sam Devlin; Frans A. Oliehoek; Rahul Savani
Publié dans: Proceedings of the Twentieth International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2021, Page(s) 1475–1477
Éditeur: IFAAMAS

Influence-aware Memory Architectures for Deep Reinforcement Learning

Auteurs: Suau, Miguel; He, Jinke; Congeduti, Elena; Starre, Rolf A. N.; Czechowski, Aleksander; Oliehoek, Frans A.
Publié dans: NeurIPS'20 Workshop on Deep Reinforcement Learning, 2020
Éditeur: arxiv

Overcoming Traffic Sensors Malfunctions with Deep Learning

Auteurs: Victoria Catalan Pastor, Elena Congeduti, Aleksander Czechowski, Frans A. Oliehoek
Publié dans: Proceedings of the 34th Benelux Conference on Artificial Intelligence (BNAIC) and the 30th Belgian Dutch Conference on Machine Learning (Benelearn), 2022
Éditeur: BNVKI

Using Bisimulation Metrics to Analyze and Evaluate Latent State Representations

Auteurs: Nele Albers, Miguel Suau, Frans A. Oliehoek
Publié dans: Proceedings of the 33rd Benelux Conference on Artificial Intelligence (BNAIC) and the 29th Belgian Dutch Conference on Machine Learning (Benelearn), 2021
Éditeur: BNAIC/Benelearn

Analog Circuit Design with Dyna-Style Reinforcement Learning

Auteurs: Wook Lee; Frans Oliehoek
Publié dans: NeurIPS 2020 Workshop: Machine Learning for Engineering Modeling, Simulation, and Design, 2020
Éditeur: Online workshop proceedings
DOI: 10.48550/arxiv.2011.07665

Learning Complex Policy Distribution with CEM Guided Adversarial Hypernetwork

Auteurs: Shi Yuan Tang; Athirai A. Irissappane; Frans A. Oliehoek; Jie Zhang
Publié dans: Proceedings of the Twentieth International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2021, Page(s) 1308–1316
Éditeur: IFAAMAS

Speeding up Deep Reinforcement Learning through Influence-Augmented Local Simulators

Auteurs: Suau, Miguel; He, Jinke; Spaan, Matthijs T. J.; Oliehoek, Frans
Publié dans: Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2022, Page(s) 1735–1737
Éditeur: IFAAMAS

BADDr: Bayes-Adaptive Deep Dropout RL for POMDPs

Auteurs: Katt, Sammie; Hai Nguyen; Frans A. Oliehoek; Christopher Amato.
Publié dans: Proceedings of the Twenty-First International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2022, ISBN 978-1-4503-9213-6
Éditeur: IFAAMAS

Poincaré-Bendixson Limit Sets in Multi-Agent Learning

Auteurs: Czechowski, Aleksander; Piliouras, Georgios
Publié dans: Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, 2022, Page(s) 318-326, ISBN 9781450392136
Éditeur: International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)

Environment Shift Games: Are Multiple Agents the Solution, and not the Problem, to Non-Stationarity?

Auteurs: Mey, Alexander; Oliehoek, Frans A
Publié dans: Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS '21), 2021, Page(s) 23–27, ISBN 978-1-4503-8307-3
Éditeur: International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)

Beyond Local Nash Equilibria for Adversarial Networks

Auteurs: Oliehoek, Frans A; Savani, Rahul; Gallego, Jose; Pol, Elise van der; Groß, Roderich
Publié dans: Benelearn 2018 Pre-proceedings, 2018
Éditeur: BNAIC

Bayesian Reinforcement Learning in Factored POMDPs

Auteurs: Katt, Sammie; Oliehoek, Frans; Amato, Christopher
Publié dans: Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, 2019
Éditeur: International Foundation for Autonomous Agents and Multiagent Systems

The Representational Capacity of Action-Value Networks for Multi-Agent Reinforcement Learning

Auteurs: Castellini, Jacopo; Oliehoek, Frans A.; Savani, Rahul; Whiteson, Shimon
Publié dans: Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, 2019, Page(s) 1862-1864, ISBN 978-1-4503-6309-9
Éditeur: International Foundation for Autonomous Agents and Multiagent Systems

Interactive Learning and Decision Making: Foundations, Insights & Challenges

Auteurs: Frans A. Oliehoek
Publié dans: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, 2018, Page(s) 5703-5708, ISBN 9780-999241127
Éditeur: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/ijcai.2018/813

Plannable Approximations to MDP Homomorphisms: Equivariance under Actions

Auteurs: van der Pol, Elise; Kipf, Thomas; Oliehoek, Frans A.; Welling, Max
Publié dans: Proceedings of the Nineteenth International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2020, Page(s) 1431--1439, ISBN 9781450375184
Éditeur: International Foundation for Autonomous Agents and Multiagent Systems

Bayesian Reinforcement Learning in Factored POMDPs

Auteurs: Katt, Sammie; Oliehoek, Frans; Amato, Christopher
Publié dans: Proceedings of the Eighteenth International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2019, Page(s) 7-15, ISBN 978-1-4503-6309-9
Éditeur: International Foundation for Autonomous Agents and Multiagent Systems

Decentralized MCTS via Learned Teammate Models

Auteurs: Aleksander Czechowski, Frans A. Oliehoek
Publié dans: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, 2020, Page(s) 81-88, ISBN 978-0-9992411-6-5
Éditeur: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/ijcai.2020/12

Maximizing Information Gain in Partially Observable Environments via Prediction Reward

Auteurs: Satsangi, Yash; Lim, Sungsu; Whiteson, Shimon; Oliehoek, Frans; White, Martha
Publié dans: Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems, 2020, Page(s) 1215--1223, ISBN 9781450375184
Éditeur: International Foundation for Autonomous Agents and Multiagent Systems

Influence-Based Abstraction in Deep Reinforcement Learning

Auteurs: Miguel Suau de Castro, Elena Congeduti, Rolf Starre, Aleksander Czechowski, Frans Oliehoek
Publié dans: AAMAS Workshop on Adaptive Learning Agents (ALA), 2019
Éditeur: https://ala2019.vub.ac.be/

Model-Based Reinforcement Learning with State Abstraction: A Survey.

Auteurs: Rolf A. N. Starre, Marco Loog, Frans A. Oliehoek.
Publié dans: In Proceedings of the 34th Benelux Conference on Artificial Intelligence (BNAIC) and the 30th Belgian Dutch Conference on Machine Learning (Benelearn), 2022
Éditeur: BNAIC/Benelearn

Alternating Maximization with Behavioral Cloning

Auteurs: Czechowski, Aleksander; Oliehoek, Frans A.
Publié dans: BNAIC/BeneLearn 2020, 2020
Éditeur: BNAIC/BeneLearn 2020

Multi Robot Surveillance and Planning in Limited Communication Environments

Auteurs: Vibhav Kedege, Aleksander Czechowski, Ludo Stellingwerff, Frans A. Oliehoek
Publié dans: Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, 2022, ISBN 978-989-758-547-0
Éditeur: SciTePress

Loss Bounds for Approximate Influence-Based Abstraction

Auteurs: Congeduti, E.; Alexander Mey; Frans Oliehoek
Publié dans: Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems, 2021, Page(s) 377-385, ISBN 9781450383073
Éditeur: International Foundation for Autonomous Agents and Multiagent Systems
DOI: 10.48550/arxiv.2011.01788

Online Planning in POMDPs with Self-Improving Simulators

Auteurs: He, Jinke; Suau de Castro, Miguel; Baier, Hendrik; Kaisers, Michael; Oliehoek, F.A.
Publié dans: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, {IJCAI-22}, 2022, Page(s) 4628--4634}
Éditeur: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/ijcai.2022/642

Multi-agent active perception with prediction rewards

Auteurs: Lauri, Mikko; Oliehoek, Frans A.
Publié dans: Advances in Neural Information Processing Systems 33 (NeurIPS 2020), Numéro 33, 2020
Éditeur: Curran Associates, Inc.

Distributed Influence-Augmented Local Simulators for Parallel MARL in Large Networked Systems

Auteurs: Miguel Suau, Jinke He, Mustafa Mert Çelikok, Matthijs T. J. Spaan, Frans A. Oliehoek
Publié dans: Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
Éditeur: NeurIPS

Comparing Exploration Approaches in Deep Reinforcement Learning for Traffic Light Control.

Auteurs: Yaniv Oren, Rolf A. N., Starre, and Frans A. Oliehoek.
Publié dans: Proceedings of the 32nd Benelux Conference on Artificial Intelligence (BNAIC) and the 29th Belgian Dutch Conference on Machine Learning (Benelearn), 2020
Éditeur: BNAIC/Benelearn

Analog Circuit Design with Dyna-Style Reinforcement Learning

Auteurs: Lee, Wook; Oliehoek, Frans A.
Publié dans: NeurIPS 2020 Workshop: Machine Learning for Engineering Modeling, Simulation, and Design, Numéro 1, 2020
Éditeur: NeurIPS 2020 Workshop: Machine Learning for Engineering Modeling, Simulation, and Design

Multi-Agent MDP Homomorphic Networks

Auteurs: Van der Pol, Elise; Herke Van Hoof; Frans A. Oliehoek; Max Welling
Publié dans: International Conference on Learning Representations, 2022
Éditeur: openreview.net

Other (3)

An Analysis of Abstracted Model-Based Reinforcement Learning.

Auteurs: Rolf A. N. Starre, Marco Loog, Frans A. Oliehoek
Publié dans: arXiv e-prints, Numéro arXiv:2208.14407, 2022
Éditeur: arXiv

The Representational Capacity of Action-Value Networks for Multi-Agent Reinforcement Learning

Auteurs: Castellini, Jacopo; Oliehoek, F.A.; Savani, Rahul; Whiteson, Shimon
Publié dans: arXiv e-prints, 2019
Éditeur: arxiv.org

A Sufficient Statistic for Influence in Structured Multiagent Environments

Auteurs: Oliehoek, Frans A.; Witwicki, Stefan; Kaelbling, Leslie P.
Publié dans: arXiv e-prints, 2019
Éditeur: arxiv.org

Peer reviewed articles (5)

Difference rewards policy gradients

Auteurs: Jacopo Castellini; Frans Oliehoek; Sam Devlin; Rahul Savani
Publié dans: Neural Computing and Applications, 2022, ISSN 0941-0643
Éditeur: Springer Verlag
DOI: 10.48550/arxiv.2012.11258

Analysing factorizations of action-value networks for cooperative multi-agent reinforcement learning

Auteurs: Jacopo Castellini; Frans A. Oliehoek; Rahul Savani; Shimon Whiteson
Publié dans: Autonomous Agents and Multi-Agent Systems, Numéro 35, 2021, ISSN 1387-2532
Éditeur: Kluwer Academic Publishers
DOI: 10.1007/s10458-021-09506-w

A Sufficient Statistic for Influence in Structured Multiagent Environments

Auteurs: Frans A. Oliehoek; Stefan J. Witwicki; Leslie Pack Kaelbling
Publié dans: Journal of Artificial Intelligence Research, Numéro 70, 2021, Page(s) 789-870, ISSN 1076-9757
Éditeur: Morgan Kaufmann Publishers, Inc.
DOI: 10.48550/arxiv.1907.09278

General-Sum Multi-Agent Continuous Inverse Optimal Control

Auteurs: Christian Neumeyer; Frans A. Oliehoek; Dariu M. Gavrila
Publié dans: IEEE Robotics and Automation Letters, Numéro 6, 2021, Page(s) 3429 - 3436, ISSN 2377-3766
Éditeur: IEEE
DOI: 10.1109/lra.2021.3060411

Influence-aware memory architectures for deep reinforcement learning in POMDPs

Auteurs: Suau, Miguel; He, Jinke; Elena Congeduti; Rolf A.N. Starre; Aleksander Czechowski; Frans A. Oliehoek
Publié dans: Neural Computing and Applications, 2022, ISSN 0941-0643
Éditeur: Springer Verlag
DOI: 10.1007/s00521-022-07691-7

Book chapters (1)

Beyond Local Nash Equilibria for Adversarial Networks

Auteurs: Frans A. Oliehoek, Rahul Savani, Jose Gallego, Elise van der Pol, Roderich Groß
Publié dans: Artificial Intelligence - 30th Benelux Conference, BNAIC 2018, ‘s-Hertogenbosch, The Netherlands, November 8–9, 2018, Revised Selected Papers, Numéro 1021, 2019, Page(s) 73-89, ISBN 978-3-030-31977-9
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-030-31978-6_7