Get our free extension to see links to code for papers anywhere online!

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
On the role of planning in model-based deep reinforcement learning

Nov 08, 2020
Jessica B. Hamrick, Abram L. Friesen, Feryal Behbahani, Arthur Guez, Fabio Viola, Sims Witherspoon, Thomas Anthony, Lars Buesing, Petar Veličković, Théophane Weber


  Access Paper or Ask Questions

Learning to Play No-Press Diplomacy with Best Response Policy Iteration

Jun 17, 2020
Thomas Anthony, Tom Eccles, Andrea Tacchetti, János Kramár, Ian Gemp, Thomas C. Hudson, Nicolas Porcel, Marc Lanctot, Julien Pérolat, Richard Everett, Satinder Singh, Thore Graepel, Yoram Bachrach


  Access Paper or Ask Questions

From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization

Feb 19, 2020
Julien Perolat, Remi Munos, Jean-Baptiste Lespiau, Shayegan Omidshafiei, Mark Rowland, Pedro Ortega, Neil Burch, Thomas Anthony, David Balduzzi, Bart De Vylder, Georgios Piliouras, Marc Lanctot, Karl Tuyls

* 43 pages 

  Access Paper or Ask Questions

OpenSpiel: A Framework for Reinforcement Learning in Games

Oct 10, 2019
Marc Lanctot, Edward Lockhart, Jean-Baptiste Lespiau, Vinicius Zambaldi, Satyaki Upadhyay, Julien Pérolat, Sriram Srinivasan, Finbarr Timbers, Karl Tuyls, Shayegan Omidshafiei, Daniel Hennes, Dustin Morrill, Paul Muller, Timo Ewalds, Ryan Faulkner, János Kramár, Bart De Vylder, Brennan Saeta, James Bradbury, David Ding, Sebastian Borgeaud, Matthew Lai, Julian Schrittwieser, Thomas Anthony, Edward Hughes, Ivo Danihelka, Jonah Ryan-Davis


  Access Paper or Ask Questions

Policy Gradient Search: Online Planning and Expert Iteration without Search Trees

Apr 07, 2019
Thomas Anthony, Robert Nishihara, Philipp Moritz, Tim Salimans, John Schulman


  Access Paper or Ask Questions

Thinking Fast and Slow with Deep Learning and Tree Search

Dec 03, 2017
Thomas Anthony, Zheng Tian, David Barber

* v1 to v2: - Add a value function in MCTS - Some MCTS hyper-parameters changed - Repetition of experiments: improved accuracy and errors shown. (note the reduction in effect size for the tpt/cat experiment) - Results from a longer training run, including changes in expert strength in training - Comparison to MoHex. v3: clarify independence of ExIt and AG0. v4: see appendix E 

  Access Paper or Ask Questions