Tor Lattimore
Tor Lattimore [1]
Tor Lattimore,
an Australian computer scientist and since 2017 research scientist at DeepMind in London, Ph.D. in 2013 with Marcus Hutter at Australian National University,
and postdoc at University of Alberta supervised by Csaba Szepesvári. His research interests include various machine learning topics and optimization problems,
in particular reinforcement learning, probably approximately correct learning
in Markov decision processes and multi-armed bandit problems.
As a chess player, and former computer chess programmer, Tor Lattimore is author of the Chess Engine Communication Protocol compatible chess engine SEE [2], which participated at various Australasian National Computer Chess Championship and CCT Tournaments.
Contents
Selected Publications
2010 ...
- Tor Lattimore, Marcus Hutter, Vaibhav Gavane (2011). Universal Prediction of Selected Bits. Algorithmic Learning Theory, Lecture Notes in Computer Science 6925, Springer, arXiv:1107.5531
- Tor Lattimore, Marcus Hutter (2011). Asymptotically Optimal Agents. Algorithmic Learning Theory, Lecture Notes in Computer Science 6925, Springer
- Tor Lattimore, Marcus Hutter (2011). Time Consistent Discounting. Algorithmic Learning Theory, Lecture Notes in Computer Science 6925, Springer, arXiv:1107.5528
- Tor Lattimore, Marcus Hutter (2011). No Free Lunch versus Occam's Razor in Supervised Learning. Solomonoff Memorial, Lecture Notes in Computer Science, Springer, arXiv:1111.3846 [5] [6]
- Tor Lattimore, Marcus Hutter (2012). PAC Bounds for Discounted MDPs. Algorithmic Learning Theory, Lecture Notes in Computer Science, Springer [7]
- Tor Lattimore, Marcus Hutter (2014). Bayesian Reinforcement Learning with Exploration. Algorithmic Learning Theory, Lecture Notes in Computer Science 8776, Springer
- Tor Lattimore, Rémi Munos (2014). Bounded Regret for Finite-Armed Structured Bandits. arXiv:1411.2919
2015 ...
- Tor Lattimore (2015). Optimally Confident UCB: Improved Regret for Finite-Armed Bandits. arXiv:1507.07880
- Tor Lattimore (2016). Regret Analysis of the Anytime Optimally Confident UCB Algorithm. arXiv:1603.08661
- Tom Everitt, Tor Lattimore, Marcus Hutter (2016). Free Lunch for Optimisation under the Universal Distribution. arXiv:1608.04544
- Tor Lattimore, Csaba Szepesvári (2017). The End of Optimism? An Asymptotic Analysis of Finite-Armed Linear Bandits. AISTATS, pdf, arXiv:1610.04491 (2016)
- Joel Veness, Tor Lattimore, Avishkar Bhoopchand, Agnieszka Grabska-Barwinska, Christopher Mattern, Peter Toth (2017). Online Learning with Gated Linear Networks. arXiv:1712.01897
- Tor Lattimore, Csaba Szepesvári (2018). Cleaning up the neighborhood: A full classification for adversarial partial monitoring. arXiv:1805.09247
- Tor Lattimore, Csaba Szepesvári (2019). Bandit Algorithms. Cambridge University Press (draft), pdf
Forum Posts
- pawn hash by Tor Lattimore, CCC, July 03, 2004 » Pawn Hash Table
- MTD Drivers by Tor Lattimore, CCC, August 10, 2004 » MTD(f)
- Verified Null-moving by Tor Lattimore, CCC, August 12, 2004 » Verified Null Move Pruning
- Qsearch Checks by Tor Lattimore, CCC, August 29, 2004 » Quiescence Search, Check
- Parsing enormous.pgn by Tor Alexander Lattimore, CCC, April 08, 2005 » Portable Game Notation
External Links
- tor (Tor Lattimore) · GitHub
- Tor Lattimore - Google+
- Lattimore, Tor FIDE Chess Profile
- Tor Lattimore chess games - 365Chess.com
- chessexpress: Ow, my brain hurts by Shaun Press, October 03, 2007
