Urmăriți
Rahul Savani
Rahul Savani
Professor of Computer Science, University of Liverpool and Alan Turing Institute
Adresă de e-mail confirmată pe liverpool.ac.uk - Pagina de pornire
Titlu
Citat de
Citat de
Anul
Lenient Multi-Agent Deep Reinforcement Learning
G Palmer, K Tuyls, D Bloembergen, R Savani
17th Int. Conf. on Autonomous Agents and Multi-Agent Systems (AAMAS), 443-451, 2018
2192018
Hedonic games
H Aziz, R Savani
Handbook of Computational Social Choice, 136-139, 2016
1882016
Hard‐to‐solve bimatrix games
R Savani, B von Stengel
Econometrica 74 (2), 397-429, 2006
1742006
Enumeration of Nash equilibria for two-player games
D Avis, GD Rosenberg, R Savani, B von Stengel
Economic Theory 42 (1), 9-37, 2010
1622010
Exponentially many steps for finding a Nash equilibrium in a bimatrix game
R Savani, B von Stengel
45th Annual IEEE Symposium on Foundations of Computer Science (FOCS), 258-267, 2004
1582004
Market Making via Reinforcement Learning
T Spooner, J Fearnley, R Savani, A Koukorinis
17th Int. Conf. on Autonomous Agents and Multi-Agent Systems (AAMAS), 434-442, 2018
150*2018
The Complexity of Gradient Descent: CLS= PPAD ∩ PLS
J Fearnley, P Goldberg, A Hollender, R Savani
Journal of the ACM 70 (1), 2023
962023
Computing stable outcomes in hedonic games
M Gairing, R Savani
International Symposium on Algorithmic Game Theory (SAGT), 174-185, 2010
842010
Mixed-species aggregations in birds: zenaida doves, Zenaida aurita, respond to the alarm calls of carib grackles, Quiscalus lugubris
AS Griffin, R Savani, K Hausmanis, L Lefebvre
Animal Behaviour 70 (3), 507-515, 2005
752005
Learning equilibria of games via payoff queries
J Fearnley, M Gairing, PW Goldberg, R Savani
The Journal of Machine Learning Research (JMLR) 16 (1), 1305-1344, 2015
742015
The Complexity of the Homotopy Method, Equilibrium Selection, and Lemke-Howson Solutions
PW Goldberg, CH Papadimitriou, R Savani
ACM Transactions on Economics and Computation (TEAC) 1 (2), 9, 2013
692013
Unique end of potential line
J Fearnley, S Gordon, R Mehta, R Savani
Journal of Computer and System Sciences (JCSS) 114, 1-35, 2020
682020
Robust market making via adversarial reinforcement learning
T Spooner, R Savani
29th International Joint Conference on Artificial Intelligence (IJCAI), 4590 …, 2020
632020
The Representational Capacity of Action-Value Networks for Multi-Agent Reinforcement Learning
J Castellini, FA Oliehoek, R Savani, S Whiteson
18th Int. Conf. on Autonomous Agents and Multi-Agent Systems (AAMAS), 1862-1864, 2019
602019
Computing approximate Nash equilibria in polymatrix games
A Deligkas, J Fearnley, R Savani, P Spirakis
Algorithmica 77 (2), 487-514, 2017
542017
Game Theory Explorer: software for the applied game theorist
R Savani, B von Stengel
Computational Management Science 12 (1), 5-33, 2015
532015
Symmetric decomposition of asymmetric games
K Tuyls, J Pérolat, M Lanctot, G Ostrovski, R Savani, JZ Leibo, T Ord, ...
Scientific reports 8 (1), 1-20, 2018
522018
Power indices in spanning connectivity games
H Aziz, O Lachish, M Paterson, R Savani
Int. Conf. on Algorithmic Applications in Management (AAIM), 55-67, 2009
492009
The Complexity of the Simplex Method
J Fearnley, R Savani
47th ACM Symposium on Theory of Computing (STOC), 201-208, 2015
442015
Beyond local Nash equilibria for adversarial networks
FA Oliehoek, R Savani, J Gallego, E van der Pol, R Groß
Benelux Conference on Artificial Intelligence, 73-89, 2018
432018
Sistemul nu poate realiza operația în acest moment. Încercați din nou mai târziu.
Articole 1–20