Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDRahul Savani
Person information
- affiliation: University of Liverpool
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2023
[j21]John Fearnley
, Paul Goldberg, Alexandros Hollender, Rahul Savani:
The Complexity of Gradient Descent: CLS = PPAD ∩ PLS. J. ACM 70(1): 7:1-7:74 (2023)- [i49]Antonia Tsili, Matthew Dyer, Vladimir Gusev, Piotr Krysta, Rahul Savani:
First Order Methods for Geometric Optimization of Crystal Structures. CoRR abs/2301.12941 (2023) - 2022
- [j20]John Fearnley, Dömötör Pálvölgyi, Rahul Savani:
A Faster Algorithm for Finding Tarski Fixed Points. ACM Trans. Algorithms 18(3): 23:1-23:23 (2022) - [c48]Ian M. Gemp, Rahul Savani, Marc Lanctot, Yoram Bachrach, Thomas W. Anthony, Richard Everett, Andrea Tacchetti, Tom Eccles, János Kramár:
Sample-based Approximation of Nash in Large Many-Player Games via Gradient Descent. AAMAS 2022: 507-515 - [c47]Joseph Jerome, Gregory Palmer, Rahul Savani:
Market Making with Scaled Beta Policies. ICAIF 2022: 214-222 - [c46]Nelson Vadori, Rahul Savani, Thomas Spooner, Sumitra Ganesh:
Consensus Multiplicative Weights Update: Learning to Learn using Projector-based Game Signatures. ICML 2022: 21901-21926 - [c45]James Butterworth, Rahul Savani, Karl Tuyls:
Generative Models over Neural Controllers for Transfer Learning. PPSN (1) 2022: 400-413 - [e2]Daniele Magazzeni, Senthil Kumar, Rahul Savani, Renyuan Xu, Carmine Ventre, Blanka Horvath, Ruimeng Hu, Tucker Balch, Francesca Toni:
3rd ACM International Conference on AI in Finance, ICAIF 2022, New York, NY, USA, November 2-4, 2022. ACM 2022, ISBN 978-1-4503-9376-8 [contents] - [i48]Joseph Jerome, Gregory Palmer, Rahul Savani:
Market Making with Scaled Beta Policies. CoRR abs/2207.03352 (2022) - [i47]Joseph Jerome, Leandro Sánchez-Betancourt, Rahul Savani, Martin Herdegen:
Model-based gym environments for limit order book trading. CoRR abs/2209.07823 (2022) - 2021
- [j19]Jacopo Castellini, Frans A. Oliehoek, Rahul Savani, Shimon Whiteson:
Analysing factorizations of action-value networks for cooperative multi-agent reinforcement learning. Auton. Agents Multi Agent Syst. 35(2): 25 (2021) - [j18]John Fearnley, Martin Gairing, Matthias Mnich, Rahul Savani:
Reachability Switching Games. Log. Methods Comput. Sci. 17(2) (2021) - [c44]Jacopo Castellini, Sam Devlin, Frans A. Oliehoek, Rahul Savani:
Difference Rewards Policy Gradients. AAMAS 2021: 1475-1477 - [c43]Rahul Savani:
The Complexity of Gradient Descent (Invited Talk). FSTTCS 2021: 5:1-5:2 - [c42]Nestoras Chalkidis, Rahul Savani:
Trading via selective classification. ICAIF 2021: 14:1-14:9 - [c41]John Fearnley, Rahul Savani:
A Faster Algorithm for Finding Tarski Fixed Points. STACS 2021: 29:1-29:16 - [c40]John Fearnley, Paul W. Goldberg, Alexandros Hollender, Rahul Savani:
The complexity of gradient descent: CLS = PPAD ∩ PLS. STOC 2021: 46-59 - [i46]Ian M. Gemp, Rahul Savani, Marc Lanctot, Yoram Bachrach, Thomas W. Anthony, Richard Everett, Andrea Tacchetti, Tom Eccles, János Kramár:
Sample-based Approximation of Nash in Large Many-Player Games via Gradient Descent. CoRR abs/2106.01285 (2021) - [i45]Nelson Vadori, Rahul Savani, Thomas Spooner, Sumitra Ganesh:
Consensus Multiplicative Weights Update: Learning to Learn using Projector-based Game Signatures. CoRR abs/2106.02615 (2021) - [i44]Nestoras Chalkidis, Rahul Savani:
Trading via Selective Classification. CoRR abs/2110.14914 (2021) - 2020
- [j17]John Fearnley, Spencer Gordon, Ruta Mehta, Rahul Savani:
Unique end of potential line. J. Comput. Syst. Sci. 114: 1-35 (2020) - [j16]Alex Singleton, Alexandros Alexiou, Rahul Savani:
Mapping the geodemographics of digital inequality in Great Britain: An integration of machine learning into small area estimation. Comput. Environ. Urban Syst. 82: 101486 (2020) - [c39]Thomas Spooner, Rahul Savani:
Robust Market Making via Adversarial Reinforcement Learning. AAMAS 2020: 2014-2016 - [c38]Gregory Palmer, Benjamin Schnieders, Rahul Savani, Karl Tuyls, Joscha-David Fossel, Harry Flore:
The Automated Inspection of Opaque Liquid Vaccines. ECAI 2020: 1898-1905 - [c37]Argyrios Deligkas, John Fearnley, Rahul Savani:
Tree Polymatrix Games Are PPAD-Hard. ICALP 2020: 38:1-38:14 - [c36]Thomas Spooner, Rahul Savani:
Robust Market Making via Adversarial Reinforcement Learning. IJCAI 2020: 4590-4596 - [c35]John Fearnley, Rasmus Ibsen-Jensen, Rahul Savani:
One-Clock Priced Timed Games are PSPACE-hard. LICS 2020: 397-409 - [i43]John Fearnley, Rasmus Ibsen-Jensen, Rahul Savani:
One-Clock Priced Timed Games are PSPACE-hard. CoRR abs/2001.04458 (2020) - [i42]Gregory Palmer, Benjamin Schnieders, Rahul Savani, Karl Tuyls, Joscha-David Fossel, Harry Flore:
The Automated Inspection of Opaque Liquid Vaccines. CoRR abs/2002.09406 (2020) - [i41]Argyrios Deligkas, John Fearnley, Rahul Savani:
Tree Polymatrix Games are PPAD-hard. CoRR abs/2002.12119 (2020) - [i40]Thomas Spooner, Rahul Savani:
Robust Market Making via Adversarial Reinforcement Learning. CoRR abs/2003.01820 (2020) - [i39]Thomas Spooner, Rahul Savani:
A Natural Actor-Critic Algorithm with Downside Risk Constraints. CoRR abs/2007.04203 (2020) - [i38]Gregory Palmer, Mark Green, Emma Boyland, Yales Stefano Rios Vasconcelos, Rahul Savani, Alex Singleton:
A deep learning approach to identify unhealthy advertisements in street view images. CoRR abs/2007.04611 (2020) - [i37]John Fearnley, Rahul Savani:
A faster algorithm for finding Tarski fixed points. CoRR abs/2010.02618 (2020) - [i36]John Fearnley, Paul W. Goldberg, Alexandros Hollender, Rahul Savani:
The Complexity of Gradient Descent: CLS = PPAD ∩ PLS. CoRR abs/2011.01929 (2020) - [i35]Jacopo Castellini, Sam Devlin, Frans A. Oliehoek, Rahul Savani:
Difference Rewards Policy Gradients. CoRR abs/2012.11258 (2020)
2010 – 2019
- 2019
- [j15]Artur Czumaj, Argyrios Deligkas, Michail Fasoulakis, John Fearnley, Marcin Jurdzinski, Rahul Savani:
Distributed Methods for Computing Approximate Equilibria. Algorithmica 81(3): 1205-1231 (2019) - [j14]Martin Gairing, Rahul Savani:
Computing Stable Outcomes in Symmetric Additively Separable Hedonic Games. Math. Oper. Res. 44(3): 1101-1121 (2019) - [j13]Martin Gairing, Rahul Savani:
Preface to the Special Issue on Algorithmic Game Theory. Theory Comput. Syst. 63(1): 2-3 (2019) - [c34]Gregory Palmer, Rahul Savani, Karl Tuyls:
Negative Update Intervals in Deep Multi-Agent Reinforcement Learning. AAMAS 2019: 43-51 - [c33]Jacopo Castellini, Frans A. Oliehoek, Rahul Savani, Shimon Whiteson:
The Representational Capacity of Action-Value Networks for Multi-Agent Reinforcement Learning. AAMAS 2019: 1862-1864 - [c32]James Butterworth, Rahul Savani, Karl Tuyls:
Evolving indoor navigational strategies using gated recurrent units in NEAT. GECCO (Companion) 2019: 111-112 - [c31]John Fearnley, Spencer Gordon, Ruta Mehta, Rahul Savani:
Unique End of Potential Line. ICALP 2019: 56:1-56:15 - [i34]Jacopo Castellini, Frans A. Oliehoek, Rahul Savani, Shimon Whiteson:
The Representational Capacity of Action-Value Networks for Multi-Agent Reinforcement Learning. CoRR abs/1902.07497 (2019) - [i33]James Butterworth, Rahul Savani, Karl Tuyls:
Evolving Indoor Navigational Strategies Using Gated Recurrent Units In NEAT. CoRR abs/1904.06239 (2019) - 2018
- [j12]Richard Klíma, Daan Bloembergen, Rahul Savani, Karl Tuyls, Alexander Wittig, Andrei Sapera, Dario Izzo:
Space Debris Removal: Learning to Cooperate and the Price of Anarchy. Frontiers Robotics AI 5: 54 (2018) - [j11]Argyrios Deligkas, John Fearnley, Rahul Savani:
Inapproximability results for constrained approximate Nash equilibria. Inf. Comput. 262: 40-56 (2018) - [j10]John Fearnley, Rahul Savani:
The Complexity of All-switches Strategy Improvement. Log. Methods Comput. Sci. 14(4) (2018) - [c30]Thomas Spooner, John Fearnley, Rahul Savani, Andreas Koukorinis:
Market Making via Reinforcement Learning. AAMAS 2018: 434-442 - [c29]Gregory Palmer, Karl Tuyls, Daan Bloembergen, Rahul Savani:
Lenient Multi-Agent Deep Reinforcement Learning. AAMAS 2018: 443-451 - [c28]Frans A. Oliehoek, Rahul Savani, Jose Gallego-Posada, Elise van der Pol, Roderich Groß:
Beyond Local Nash Equilibria for Adversarial Networks. BNCAI 2018: 73-89 - [c27]John Fearnley, Martin Gairing, Matthias Mnich, Rahul Savani:
Reachability Switching Games. ICALP 2018: 124:1-124:14 - [i32]John Fearnley, Spencer Gordon, Ruta Mehta, Rahul Savani:
End of Potential Line. CoRR abs/1804.03450 (2018) - [i31]Thomas Spooner, John Fearnley, Rahul Savani, Andreas Koukorinis:
Market Making via Reinforcement Learning. CoRR abs/1804.04216 (2018) - [i30]Frans A. Oliehoek, Rahul Savani, Jose Gallego-Posada, Elise van der Pol, Roderich Groß:
Beyond Local Nash Equilibria for Adversarial Networks. CoRR abs/1806.07268 (2018) - [i29]Gregory Palmer, Rahul Savani, Karl Tuyls:
Negative Update Intervals in Deep Multi-Agent Reinforcement Learning. CoRR abs/1809.05096 (2018) - [i28]John Fearnley, Spencer Gordon, Ruta Mehta, Rahul Savani:
Unique End of Potential Line. CoRR abs/1811.03841 (2018) - 2017
- [j9]Argyrios Deligkas, John Fearnley, Rahul Savani, Paul G. Spirakis:
Computing Approximate Nash Equilibria in Polymatrix Games. Algorithmica 77(2): 487-514 (2017) - [c26]Frans A. Oliehoek, Rahul Savani, Elliot Adderton, Xia Cui, David Jackson, Phil Jimmieson, John Christopher Jones, Keith Kennedy, Ben Mason, Adam Plumbley, Luke Dawson:
LiftUpp: Support to Develop Learner Performance. AIED 2017: 553-556 - [c25]Argyrios Deligkas, John Fearnley, Rahul Savani:
Computing Constrained Approximate Equilibria in Polymatrix Games. SAGT 2017: 93-105 - [i27]John Fearnley, Spencer Gordon, Ruta Mehta, Rahul Savani:
CLS: New Problems and Completeness. CoRR abs/1702.06017 (2017) - [i26]Frans A. Oliehoek, Rahul Savani, Elliot Adderton, Xia Cui, David Jackson, Phil Jimmieson, John Christopher Jones, Keith Kennedy, Ben Mason, Adam Plumbley, Luke Dawson:
LiftUpp: Support to develop learner performance. CoRR abs/1704.06549 (2017) - [i25]Argyrios Deligkas, John Fearnley, Rahul Savani:
Computing Constrained Approximate Equilibria in Polymatrix Games. CoRR abs/1705.02266 (2017) - [i24]Gregory Palmer, Karl Tuyls, Daan Bloembergen, Rahul Savani:
Lenient Multi-Agent Deep Reinforcement Learning. CoRR abs/1707.04402 (2017) - [i23]John Fearnley, Martin Gairing, Matthias Mnich, Rahul Savani:
Reachability Switching Games. CoRR abs/1709.08991 (2017) - [i22]Karl Tuyls, Julien Pérolat, Marc Lanctot, Georg Ostrovski, Rahul Savani, Joel Z. Leibo, Toby Ord, Thore Graepel, Shane Legg:
Symmetric Decomposition of Asymmetric Games. CoRR abs/1711.05074 (2017) - [i21]Frans A. Oliehoek, Rahul Savani, Jose Gallego-Posada, Elise van der Pol, Edwin D. de Jong, Roderich Gross:
GANGs: Generative Adversarial Network Games. CoRR abs/1712.00679 (2017) - 2016
- [j8]John Fearnley, Paul W. Goldberg, Rahul Savani, Troels Bjerre Sørensen:
Approximate Well-supported Nash Equilibria Below Two-thirds. Algorithmica 76(2): 297-319 (2016) - [j7]Richard Klíma, Daan Bloembergen, Rahul Savani, Karl Tuyls, Daniel Hennes, Dario Izzo:
Space Debris Removal: A Game Theoretic Analysis. Games 7(3): 20 (2016) - [j6]John Fearnley, Rahul Savani:
Finding Approximate Nash Equilibria of Bimatrix Games via Payoff Queries. ACM Trans. Economics and Comput. 4(4): 25:1-25:19 (2016) - [c24]Argyrios Deligkas, John Fearnley, Tobenna Peter Igwe, Rahul Savani:
An Empirical Study on Computing Equilibria in Polymatrix Games. AAMAS 2016: 186-195 - [c23]Richard Klíma, Daan Bloembergen, Rahul Savani, Karl Tuyls, Daniel Hennes, Dario Izzo:
Space Debris Removal: A Game Theoretic Analysis. ECAI 2016: 1658-1659 - [c22]John Fearnley, Rahul Savani:
The Complexity of All-switches Strategy Improvement. SODA 2016: 130-139 - [c21]Artur Czumaj, Argyrios Deligkas, Michail Fasoulakis, John Fearnley, Marcin Jurdzinski, Rahul Savani:
Distributed Methods for Computing Approximate Equilibria. WINE 2016: 15-28 - [c20]Argyrios Deligkas, John Fearnley, Rahul Savani:
Inapproximability Results for Approximate Nash Equilibria. WINE 2016: 29-43 - [e1]Martin Gairing, Rahul Savani:
Algorithmic Game Theory - 9th International Symposium, SAGT 2016, Liverpool, UK, September 19-21, 2016. Proceedings. Lecture Notes in Computer Science 9928, Springer 2016, ISBN 978-3-662-53353-6 [contents] - [r1]Haris Aziz, Rahul Savani:
Hedonic Games. Handbook of Computational Social Choice 2016: 356-376 - [i20]Argyrios Deligkas, John Fearnley, Tobenna Peter Igwe, Rahul Savani:
An Empirical Study on Computing Equilibria in Polymatrix Games. CoRR abs/1602.06865 (2016) - [i19]Argyrios Deligkas, John Fearnley, Rahul Savani:
Inapproximability Results for Approximate Nash Equilibria. CoRR abs/1608.03574 (2016) - 2015
- [j5]Rahul Savani, Bernhard von Stengel:
Game Theory Explorer: software for the applied game theorist. Comput. Manag. Sci. 12(1): 5-33 (2015) - [j4]John Fearnley, Martin Gairing, Paul W. Goldberg, Rahul Savani:
Learning equilibria of games via payoff queries. J. Mach. Learn. Res. 16: 1305-1344 (2015) - [c19]John Fearnley, Rahul Savani:
The Complexity of the Simplex Method. STOC 2015: 201-208 - [c18]John Fearnley, Tobenna Peter Igwe, Rahul Savani:
An Empirical Study of Finding Approximate Equilibria in Bimatrix Games. SEA 2015: 339-351 - [i18]Rahul Savani, Bernhard von Stengel:
Unit Vector Games. CoRR abs/1501.02243 (2015) - [i17]John Fearnley, Tobenna Peter Igwe, Rahul Savani:
An Empirical Study of Finding Approximate Equilibria in Bimatrix Games. CoRR abs/1502.04980 (2015) - [i16]John Fearnley, Rahul Savani:
The Complexity of All-switches Strategy Improvement. CoRR abs/1507.04500 (2015) - [i15]Martin Gairing, Rahul Savani:
Computing stable outcomes in symmetric additively-separable hedonic games. CoRR abs/1509.05322 (2015) - [i14]Artur Czumaj, Argyrios Deligkas, Michail Fasoulakis, John Fearnley, Marcin Jurdzinski, Rahul Savani:
Distributed Methods for Computing Approximate Equilibria. CoRR abs/1512.03315 (2015) - 2014
- [c17]Mingyu Guo, Argyrios Deligkas, Rahul Savani:
Increasing VCG Revenue by Decreasing the Quality of Items. AAAI 2014: 705-711 - [c16]Yoram Bachrach, Rahul Savani, Nisarg Shah:
Cooperative max games and agent failures. AAMAS 2014: 29-36 - [c15]John Fearnley, Rahul Savani:
Finding approximate Nash equilibria of bimatrix games via payoff queries. EC 2014: 657-674 - [c14]Paul Devine, Rahul Savani:
A data rich money market model - agent-based modelling for financial stability. SIMULTECH 2014: 231-236 - [c13]Argyrios Deligkas, John Fearnley, Rahul Savani, Paul G. Spirakis:
Computing Approximate Nash Equilibria in Polymatrix Games. WINE 2014: 58-71 - [i13]Rahul Savani, Bernhard von Stengel:
Game Theory Explorer - Software for the Applied Game Theorist. CoRR abs/1403.3969 (2014) - [i12]John Fearnley, Rahul Savani:
The Complexity of the Simplex Method. CoRR abs/1404.0605 (2014) - [i11]Argyrios Deligkas, John Fearnley, Rahul Savani, Paul G. Spirakis:
Computing Approximate Nash Equilibria in Polymatrix Games. CoRR abs/1409.3741 (2014) - [i10]Nimrod Megiddo, Kurt Mehlhorn, Rahul Savani, Vijay V. Vazirani:
Equilibrium Computation (Dagstuhl Seminar 14342). Dagstuhl Reports 4(8): 73-88 (2014) - 2013
- [j3]Paul W. Goldberg, Rahul Savani, Troels Bjerre Sørensen, Carmine Ventre:
On the approximation performance of fictitious play in finite games. Int. J. Game Theory 42(4): 1059-1083 (2013) - [j2]Paul W. Goldberg, Christos H. Papadimitriou, Rahul Savani:
The Complexity of the Homotopy Method, Equilibrium Selection, and Lemke-Howson Solutions. ACM Trans. Economics and Comput. 1(2): 9:1-9:25 (2013) - [c12]John Fearnley, Martin Gairing, Paul W. Goldberg, Rahul Savani:
Learning equilibria of games via payoff queries. EC 2013: 397-414 - [c11]Yogesh Anbalagan, Sergey Norin, Rahul Savani, Adrian Vetta:
Polylogarithmic Supports Are Required for Approximate Well-Supported Nash Equilibria below 2/3. WINE 2013: 15-23 - [i9]John Fearnley, Martin Gairing, Paul W. Goldberg, Rahul Savani:
Learning Equilibria of Games via Payoff Queries. CoRR abs/1302.3116 (2013) - [i8]Yogesh Anbalagan, Sergey Norin, Rahul Savani, Adrian Vetta:
Polylogarithmic Supports are required for Approximate Well-Supported Nash Equilibria below 2/3. CoRR abs/1309.7258 (2013) - [i7]John Fearnley, Rahul Savani:
Finding Approximate Nash Equilibria of Bimatrix Games via Payoff Queries. CoRR abs/1310.7419 (2013) - 2012
- [j1]Rahul Savani:
High-Frequency Trading: The Faster, the Better? IEEE Intell. Syst. 27(4): 70-73 (2012) - [c10]John Fearnley, Paul W. Goldberg, Rahul Savani, Troels Bjerre Sørensen:
Approximate Well-Supported Nash Equilibria Below Two-Thirds. SAGT 2012: 108-119 - [i6]John Fearnley, Paul W. Goldberg, Rahul Savani, Troels Bjerre Sørensen:
Approximate Well-supported Nash Equilibria below Two-thirds. CoRR abs/1204.0707 (2012) - 2011
- [c9]Martin Gairing, Rahul Savani:
Computing stable outcomes in hedonic games with voting-based deviations. AAMAS 2011: 559-566 - [c8]Paul W. Goldberg, Rahul Savani, Troels Bjerre Sørensen, Carmine Ventre:
On the Approximation Performance of Fictitious Play in Finite Games. ESA 2011: 93-105 - [c7]Paul W. Goldberg, Christos H. Papadimitriou, Rahul Savani:
The Complexity of the Homotopy Method, Equilibrium Selection, and Lemke-Howson Solutions. FOCS 2011: 67-76 - [i5]Paul W. Goldberg, Rahul Savani, Troels Bjerre Sørensen, Carmine Ventre:
On the Approximation Performance of Fictitious Play in Finite Games. CoRR abs/1103.1040 (2011) - 2010
- [c6]Martin Gairing, Rahul Savani:
Computing Stable Outcomes in Hedonic Games. SAGT 2010: 174-185 - [c5]John Fearnley, Marcin Jurdzinski, Rahul Savani:
Linear Complementarity Algorithms for Infinite Games. SOFSEM 2010: 382-393 - [i4]Paul W. Goldberg, Christos H. Papadimitriou, Rahul Savani:
The Complexity of the Homotopy Method, Equilibrium Selection, and Lemke-Howson Solutions. CoRR abs/1006.5352 (2010)
2000 – 2009
- 2009
- [c4]Haris Aziz, Oded Lachish, Mike Paterson, Rahul Savani:
Power Indices in Spanning Connectivity Games. AAIM 2009: 55-67 - [c3]Haris Aziz, Oded Lachish, Mike Paterson, Rahul Savani:
Wiretapping a Hidden Network. WINE 2009: 438-446 - [i3]Haris Aziz, Oded Lachish, Mike Paterson, Rahul Savani:
Spanning connectivity games. CoRR abs/0906.3643 (2009) - [i2]Haris Aziz, Oded Lachish, Mike Paterson, Rahul Savani:
Wiretapping a hidden network. CoRR abs/0909.5293 (2009) - [i1]John Fearnley, Marcin Jurdzinski, Rahul Savani:
Linear Complementarity Algorithms for Infinite Games. CoRR abs/0909.5653 (2009) - 2008
- [c2]Marcin Jurdzinski, Rahul Savani:
A Simple P-Matrix Linear Complementarity Problem for Discounted Games. CiE 2008: 283-293 - 2004
- [c1]Rahul Savani, Bernhard von Stengel:
Exponentially Many Steps for Finding a Nash Equilibrium in a Bimatrix Game. FOCS 2004: 258-267
Coauthor Index