Up a level |
Spooner, Thomas ORCID: 0000-0002-1732-7582
(2021)
Algorithmic Trading and Reinforcement Learning: Robust methodologies for AI in finance.
PhD thesis, University of Liverpool.
Zhou, Y
(2018)
Analysing Large-scale Surveillance Video.
PhD thesis, University of Liverpool.
Castellini, Jacopo, Oliehoek, Frans A ORCID: 0000-0003-4372-5055, Savani, Rahul ORCID: 0000-0003-1262-7831 and Whiteson, Shimon
(2021)
Analysing factorizations of action-value networks for cooperative multi-agent reinforcement learning.
AUTONOMOUS AGENTS AND MULTI-AGENT SYSTEMS, 35 (2).
25-.
Fearnley, John, Goldberg, Paul W, Savani, Rahul ORCID: 0000-0003-1262-7831 and Sørensen, Troels Bjerre
(2016)
Approximate Well-supported Nash Equilibria Below Two-thirds.
Algorithmica, 76 (2).
pp. 297-319.
Spooner, Thomas ORCID: 0000-0002-1732-7582, Jones, Anne E, Fearnley, John, Savani, Rahul ORCID: 0000-0003-1262-7831, Turner, Joanne ORCID: 0000-0002-0258-2353 and Baylis, Matthew ORCID: 0000-0003-0335-187X
(2020)
Bayesian optimisation of restriction zones for bluetongue control.
Scientific Reports, 10 (1).
p. 15139.
Oliehoek, Frans A ORCID: 0000-0003-4372-5055, Savani, Rahul ORCID: 0000-0003-1262-7831, Gallego, Jose, van der Pol, Elise and Gross, Roderich
(2019)
Beyond Local Nash Equilibria for Adversarial Networks.
Springer International Publishing.
Hansen, Kristoffer Arnsfelt, Ibsen-Jensen, Rasmus and Koucky, Michal
(2016)
The Big Match in Small Space (Extended Abstract).
.
Fearnley, John, Gordon, Spencer, Mehta, Ruta and Savani, Rahul ORCID: 0000-0003-1262-7831
(2017)
CLS: New Problems and Completeness.
.
(Unpublished)
Fearnley, John, Goldberg, Paul W, Hollender, Alexandros and Savani, Rahul ORCID: 0000-0003-1262-7831
(2021)
The Complexity of Gradient Descent: CLS = PPAD ∧ PLS.
STOC '21: PROCEEDINGS OF THE 53RD ANNUAL ACM SIGACT SYMPOSIUM ON THEORY OF COMPUTING, abs/20.
pp. 46-59.
Fearnley, John, Goldberg, Paul, Hollender, Alexandros and Savani, Rahul ORCID: 0000-0003-1262-7831
(2023)
The Complexity of Gradient Descent: CLS = PPAD ∧ PLS.
JOURNAL OF THE ACM, 70 (1).
pp. 1-74.
Fearnley, John and Savani, Rahul ORCID: 0000-0003-1262-7831
(2015)
The Complexity of the Simplex Method.
In: 47th annual ACM Symposium on Theory of Computing (STOC '15), 2015-6-14 - 2015-6-17.
Deligkas, Argyrios, Fearnley, John, Savani, Rahul ORCID: 0000-0003-1262-7831 and Spirakis, Paul ORCID: 0000-0001-5396-3749
(2017)
Computing Approximate Nash Equilibria in Polymatrix Games.
ALGORITHMICA, 77 (2).
pp. 487-514.
Deligkas, Argyrios, Fearnley, John, Savani, Rahul and Spirakis, Paul G
(2017)
Computing Approximate Nash Equilibria in Polymatrix Games.
Algorithmica, 77.
487 - 514.
Gairing, Martin and Savani, Rahul ORCID: 0000-0003-1262-7831
(2019)
Computing Stable Outcomes in Symmetric Additively Separable Hedonic Games.
Math. Oper. Res., 44.
pp. 1101-1121.
Coletta, Andrea ORCID: 0000-0003-1401-1715, Jerome, Joseph ORCID: 0000-0002-8312-0053, Savani, Rahul ORCID: 0000-0003-1262-7831 and Vyetrenko, Svitlana ORCID: 0000-0001-7650-9880
(2023)
Conditional Generators for Limit Order Book Environments: Explainability, Challenges, and Robustness.
In: ICAIF '23: 4th ACM International Conference on AI in Finance.
Vadori, Nelson, Savani, Rahul ORCID: 0000-0003-1262-7831, Spooner, Thomas and Ganesh, Sumitra
(2022)
Consensus Multiplicative Weights Update: Learning to Learn using Projector-based Game Signatures.
In: International Conference on Machine Learning (ICML).
Bachrach, Yoram, Savani, Rahul ORCID: 0000-0003-1262-7831 and Shah, Nisarg
(2014)
Cooperative Max Games and Agent Failures.
In: 13th Inter- national Conference on Autonomous Agents and Multiagent Systems (AAMAS 2014), 2014-5-5 - 2014-5-9, Paris, France.
Castellini, Jacopo, Devlin, Sam, Oliehoek, Frans A ORCID: 0000-0003-4372-5055 and Savani, Rahul ORCID: 0000-0003-1262-7831
(2020)
Difference Rewards Policy Gradients.
[Internet Publication]
Castellini, Jacopo, Devlin, Sam, Oliehoek, Frans A ORCID: 0000-0003-4372-5055 and Savani, Rahul ORCID: 0000-0003-1262-7831
(2022)
Difference rewards policy gradients.
.
Czumaj, Artur, Deligkas, Argyrios, Fasoulakis, Michail, Fearnley, JS, Jurdzinski, Marcin and Savani, Rahul ORCID: 0000-0003-1262-7831
(2019)
Distributed Methods for Computing Approximate Equilibria.
Algorithmica: an international journal in computer science, 81 (3).
pp. 1205-1231.
Igwe, Tobenna
(2018)
An Empirical Study on Computation of Exact and Approximate Equilibria.
PhD thesis, University of Liverpool.
Fearnley, John, Gordon, Spencer, Mehta, Ruta and Savani, Rahul ORCID: 0000-0003-1262-7831
(2018)
End of Potential Line.
.
Fearnley, John and Savani, Rahul ORCID: 0000-0003-1262-7831
(2021)
A Faster Algorithm for Finding Tarski Fixed Points.
38TH INTERNATIONAL SYMPOSIUM ON THEORETICAL ASPECTS OF COMPUTER SCIENCE (STACS 2021), 187.
Fearnley, John, Palvolgyi, Domotor and Savani, Rahul ORCID: 0000-0003-1262-7831
(2022)
A Faster Algorithm for Finding Tarski Fixed Points.
ACM TRANSACTIONS ON ALGORITHMS, 18 (3).
29:1-29:1.
Fearnley, John, Pálvölgyi, Dömötör and Savani, Rahul ORCID: 0000-0003-1262-7831
(2022)
A Faster Algorithm for Finding Tarski Fixed Points.
ACM Transactions on Algorithms, 18 (3).
pp. 1-23.
Oliehoek, Frans A ORCID: 0000-0003-4372-5055, Savani, Rahul ORCID: 0000-0003-1262-7831, Gallego-Posada, Jose, Pol, Elise van der, Jong, Edwin D de and Gross, Roderich
(2017)
GANGs: Generative Adversarial Network Games.
.
(Unpublished)
Savani, Rahul ORCID: 0000-0003-1262-7831 and von Stengel, Bernhard
(2015)
Game Theory Explorer: software for the applied game theorist.
COMPUTATIONAL MANAGEMENT SCIENCE, 12 (1).
pp. 5-33.
Castellini, Jacopo
(2022)
Improved Representations for Cooperative Multi-Agent Reinforcement Learning.
Doctor of Philosophy thesis, University of Liverpool.
Deligkas, Argyrios, Fearnley, John and Savani, Rahul ORCID: 0000-0003-1262-7831
(2016)
Inapproximability Results for Approximate Nash Equilibria.
.
Deligkas, Argyrios, Fearnley, John and Savani, Rahul ORCID: 0000-0003-1262-7831
(2016)
Inapproximability Results for Approximate Nash Equilibria.
In: WINE 2016: The 12th Conference on Web and Internet Economics.
Deligkas, Argyrios, Fearnley, JS and Savani, Rahul ORCID: 0000-0003-1262-7831
(2018)
Inapproximability results for constrained approximate Nash equilibria.
Information and Computation, 262 (1).
pp. 40-56.
Guo, Mingyu, Deligkas, Argyrios and Savani, Rahul ORCID: 0000-0003-1262-7831
(2014)
Increasing VCG Revenue by Decreasing the Quality of Items.
In: AAAI Conference on Artificial Intelligence Twenty-Eighth AAAI Conference on Artificial Intelligence, Québec City, Québec, Canada.
Palmer, Gregory
(2020)
Independent Learning Approaches: Overcoming Multi-Agent Learning Pathologies In Team-Games.
PhD thesis, University of Liverpool.
Palmer, Gregory, Tuyls, Karl, Bloembergen, Daan and Savani, Rahul ORCID: 0000-0003-1262-7831
(2018)
Lenient Multi-Agent Deep Reinforcement Learning.
.
Palmer, Gregory, Tuyls, Karl, Bloembergen, Daan and Savani, Rahul ORCID: 0000-0003-1262-7831
(2018)
Lenient Multi-Agent Deep Reinforcement Learning.
In: International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Stockholm.
Butterworth, James ORCID: 0000-0002-6446-6577
(2023)
Manifolds & Memory: Improving the Search Speed of Evolutionary Algorithms.
PhD thesis, University of Liverpool.
Singleton, Alex, Alexiou, Alexandros ORCID: 0000-0003-3533-3238 and Savani, Rahul ORCID: 0000-0003-1262-7831
(2020)
Mapping the geodemographics of digital inequality in Great Britain: An integration of machine learning into small area estimation.
Computers, Environment and Urban Systems, 82.
p. 101486.
Spooner, Thomas ORCID: 0000-0002-1732-7582, Fearnley, John, Savani, Rahul ORCID: 0000-0003-1262-7831 and Koukorinis, Andreas
(2018)
Market Making via Reinforcement Learning.
.
Spooner, Thomas ORCID: 0000-0002-1732-7582, Fearnley, John, Savani, Rahul ORCID: 0000-0003-1262-7831 and Koukorinis, Andreas
(2018)
Market Making via Reinforcement Learning.
In: AAMAS 2018.
Jerome, Joseph ORCID: 0000-0002-8312-0053, Sánchez-Betancourt, Leandro ORCID: 0000-0001-6447-7105, Savani, Rahul ORCID: 0000-0003-1262-7831 and Herdegen, Martin ORCID: 0000-0002-2092-7167
(2023)
Mbt-gym: Reinforcement learning for model-based limit order book trading.
In: ICAIF '23: 4th ACM International Conference on AI in Finance.
Klima, R
(2019)
Multi-Agent Learning for Security and Sustainability.
PhD thesis, University of Liverpool.
Palmer, Gregory, Savani, Rahul ORCID: 0000-0003-1262-7831 and Tuyls, Karl
(2019)
Negative Update Intervals in Deep Multi-Agent Reinforcement Learning.
.
Fearnley, John, Ibsen-Jensen, Rasmus and Savani, Rahul ORCID: 0000-0003-1262-7831
(2020)
One-Clock Priced Timed Games are PSPACE-hard.
LICS '20: Proceedings of the 35th Annual ACM/IEEE Symposium on Logic in Computer Science, abs/20.
pp. 397-409.
Fearnley, John, Ibsen-Jensen, Rasmus and Savani, Rahul
(2020)
One-Clock Priced Timed Games are PSPACE-hard.
.
Anbalagan, Yogesh, Norin, Sergey, Savani, Rahul ORCID: 0000-0003-1262-7831 and Vetta, Adrian
(2013)
Polylogarithmic Supports are required for Approximate Well-Supported
Nash Equilibria below 2/3.
In: The 9th Conference on Web and Internet Economics (WINE), 2013-12-11 - 2013-12-14, Harvard.
Gairing, Martin and Savani, Rahul ORCID: 0000-0003-1262-7831
(2019)
Preface to the Special Issue on Algorithmic Game Theory.
THEORY OF COMPUTING SYSTEMS, 63 (1).
pp. 2-3.
Fearnley, John, Gairing, Martin, Mnich, Matthias and Savani, Rahul ORCID: 0000-0003-1262-7831
(2021)
REACHABILITY SWITCHING GAMES.
In: ICALP 2018.
Fearnley, John, Gairing, Martin, Mnich, Matthias and Savani, Rahul ORCID: 0000-0003-1262-7831
(2017)
Reachability Switching Games.
.
Fletcher, Amelia, Ormosi, Peter L and Savani, Rahul ORCID: 0000-0003-1262-7831
(2023)
Recommender Systems and Supplier Competition on Platforms.
Journal of Competition Law and Economics, 19 (3).
pp. 397-426.
Zamaraeva, Elena, Collins, Christopher M ORCID: 0000-0002-0101-4426, Antypov, Dmytro ORCID: 0000-0003-1893-7785, Gusev, Vladimir V, Savani, Rahul ORCID: 0000-0003-1262-7831, Dyer, Matthew Stephen ORCID: 0000-0002-4923-3003, Darling, George ORCID: 0000-0001-9329-9993, Potapov, Igor, Rosseinsky, Matthew J ORCID: 0000-0002-1910-2483 and Spirakis, Paul G ORCID: 0000-0001-5396-3749
(2023)
Reinforcement Learning in Crystal Structure Prediction.
Digital Discovery, 2 (6).
pp. 1831-1840.
Castellini, Jacopo, Oliehoek, Frans A ORCID: 0000-0003-4372-5055, Savani, Rahul and Whiteson, Shimon
(2019)
The Representational Capacity of Action-Value Networks for Multi-Agent Reinforcement Learning.
[Internet Publication]
Spooner, Thomas ORCID: 0000-0002-1732-7582 and Savani, Rahul ORCID: 0000-0003-1262-7831
(2020)
Robust Market Making via Adversarial Reinforcement Learning.
.
Klima, Richard, Bloembergen, Daan, Savani, Rahul ORCID: 0000-0003-1262-7831, Tuyls, Karl, Hennes, Daniel and Izzo, Dario
(2016)
Space Debris Removal: A Game Theoretic Analysis.
In: European Conference on Artificial Intelligence (ECAI), 2016-8-29 - 2016-9-2, The Hague, NL.
Klima, Richard, Bloembergen, Daan, Savani, Rahul ORCID: 0000-0003-1262-7831, Tuyls, Karl, Wittig, Alexander, Sapera, Andrei and Izzo, Dario
(2018)
Space Debris Removal: Learning to Cooperate and the Price of Anarchy.
Frontiers in Robotics and AI, 5 (JUN).
54-.
Aziz, Haris, Lachish, Oded, Paterson, Mike and Savani, Rahul ORCID: 0000-0003-1262-7831
(2009)
Spanning connectivity games.
[Report]
(Unpublished)
Tuyls, Karl, Perolat, Julien, Lanctot, Marc, Ostrovski, Georg, Savani, Rahul ORCID: 0000-0003-1262-7831, Leibo, Joel, Ord, Toby, Graepel, Thore and Legg, Shane
(2018)
Symmetric Decomposition of Asymmetric Games.
Scientific Reports, 8 (1).
1015-.
Chalkidis, Nestoras and Savani, Rahul ORCID: 0000-0003-1262-7831
(2021)
Trading via Selective Classification.
.
Deligkas, Argyrios, Fearnley, John and Savani, Rahul ORCID: 0000-0003-1262-7831
(2020)
Tree Polymatrix Games Are PPAD-Hard.
In: ICALP 2020.
Deligkas, Argyrios, Fearnley, John and Savani, Rahul ORCID: 0000-0003-1262-7831
(2020)
Tree Polymatrix Games are PPAD-hard.
In: 47th International Colloquium on Automata, Languages, and Programming (ICALP 2020), 2020-7-8 - 2020-7-12, Beijing.
Fearnley, JS, Gordon, Spencer, Mehta, Ruta and Savani, Rahul ORCID: 0000-0003-1262-7831
(2020)
Unique End of Potential Line.
Journal of Computer and System Sciences, 114.
pp. 1-35.
Fearnley, John, Gordon, Spencer, Mehta, Ruta and Savani, Rahul ORCID: 0000-0003-1262-7831
(2018)
Unique End of Potential Line.
.
Savani, Rahul ORCID: 0000-0003-1262-7831 and von Stengel, Bernhard
(2016)
Unit vector games.
INTERNATIONAL JOURNAL OF ECONOMIC THEORY, 12 (1).
pp. 7-27.
Palmer, Gregory, Green, Mark ORCID: 0000-0002-0942-6628, Boyland, Emma ORCID: 0000-0001-8384-4994, Vasconcelos, Yales Stefano Rios, Savani, Rahul ORCID: 0000-0003-1262-7831 and Singleton, Alex
(2021)
A deep learning approach to identify unhealthy advertisements in street view images.
SCIENTIFIC REPORTS, 11 (1).
4884-.