Zobrazeno 1 - 10
of 106
pro vyhledávání: '"Burch, Neil"'
Search in test time is often used to improve the performance of reinforcement learning algorithms. Performing theoretically sound search in fully adversarial two-player games with imperfect information is notoriously difficult and requires a complica
Externí odkaz:
http://arxiv.org/abs/2312.15220
Autor:
Lanctot, Marc, Schultz, John, Burch, Neil, Smith, Max Olan, Hennes, Daniel, Anthony, Thomas, Perolat, Julien
Progress in fields of machine learning and adversarial planning has benefited significantly from benchmark domains, from checkers and the classic UCI data sets to Go and Diplomacy. In sequential decision-making, agent evaluation has largely been rest
Externí odkaz:
http://arxiv.org/abs/2303.03196
Autor:
Perolat, Julien, de Vylder, Bart, Hennes, Daniel, Tarassov, Eugene, Strub, Florian, de Boer, Vincent, Muller, Paul, Connor, Jerome T., Burch, Neil, Anthony, Thomas, McAleer, Stephen, Elie, Romuald, Cen, Sarah H., Wang, Zhe, Gruslys, Audrunas, Malysheva, Aleksandra, Khan, Mina, Ozair, Sherjil, Timbers, Finbarr, Pohlen, Toby, Eccles, Tom, Rowland, Mark, Lanctot, Marc, Lespiau, Jean-Baptiste, Piot, Bilal, Omidshafiei, Shayegan, Lockhart, Edward, Sifre, Laurent, Beauguerlange, Nathalie, Munos, Remi, Silver, David, Singh, Satinder, Hassabis, Demis, Tuyls, Karl
We introduce DeepNash, an autonomous agent capable of learning to play the imperfect information game Stratego from scratch, up to a human expert level. Stratego is one of the few iconic board games that Artificial Intelligence (AI) has not yet maste
Externí odkaz:
http://arxiv.org/abs/2206.15378
Autor:
Schmid, Martin, Moravcik, Matej, Burch, Neil, Kadlec, Rudolf, Davidson, Josh, Waugh, Kevin, Bard, Nolan, Timbers, Finbarr, Lanctot, Marc, Holland, G. Zacharias, Davoodi, Elnaz, Christianson, Alden, Bowling, Michael
Publikováno v:
Science Advances 9, eadg3256 (2023)
Games have a long history as benchmarks for progress in artificial intelligence. Approaches using search and learning produced strong performance across many perfect information games, and approaches using game-theoretic reasoning and learning demons
Externí odkaz:
http://arxiv.org/abs/2112.03178
Autor:
Sokota, Samuel, Lockhart, Edward, Timbers, Finbarr, Davoodi, Elnaz, D'Orazio, Ryan, Burch, Neil, Schmid, Martin, Bowling, Michael, Lanctot, Marc
For artificially intelligent learning systems to have widespread applicability in real-world settings, it is important that they be able to operate decentrally. Unfortunately, decentralized control is difficult -- computing even an epsilon-optimal jo
Externí odkaz:
http://arxiv.org/abs/2101.04237
Autor:
Lockhart, Edward, Burch, Neil, Bard, Nolan, Borgeaud, Sebastian, Eccles, Tom, Smaira, Lucas, Smith, Ray
We introduce a human-compatible reinforcement-learning approach to a cooperative game, making use of a third-party hand-coded human-compatible bot to generate initial training data and to perform initial evaluation. Our learning approach consists of
Externí odkaz:
http://arxiv.org/abs/2011.14124
Search has played a fundamental role in computer game research since the very beginning. And while online search has been commonly used in perfect information games such as Chess and Go, online search methods for imperfect information games have only
Externí odkaz:
http://arxiv.org/abs/2006.08740
Autor:
Timbers, Finbarr, Bard, Nolan, Lockhart, Edward, Lanctot, Marc, Schmid, Martin, Burch, Neil, Schrittwieser, Julian, Hubert, Thomas, Bowling, Michael
Researchers have demonstrated that neural networks are vulnerable to adversarial examples and subtle environment changes, both of which one can view as a form of distribution shift. To humans, the resulting errors can look like blunders, eroding trus
Externí odkaz:
http://arxiv.org/abs/2004.09677
Autor:
Perolat, Julien, Munos, Remi, Lespiau, Jean-Baptiste, Omidshafiei, Shayegan, Rowland, Mark, Ortega, Pedro, Burch, Neil, Anthony, Thomas, Balduzzi, David, De Vylder, Bart, Piliouras, Georgios, Lanctot, Marc, Tuyls, Karl
In this paper we investigate the Follow the Regularized Leader dynamics in sequential imperfect information games (IIG). We generalize existing results of Poincar\'e recurrence from normal-form games to zero-sum two-player imperfect information games
Externí odkaz:
http://arxiv.org/abs/2002.08456
Multiagent decision-making in partially observable environments is usually modelled as either an extensive-form game (EFG) in game theory or a partially observable stochastic game (POSG) in multiagent reinforcement learning (MARL). One issue with the
Externí odkaz:
http://arxiv.org/abs/1906.11110