Daniel Toyama — accepted AI-conference papers

2024

Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu Search

Abbas Mehrabian, Ankit Anand, Hyunjik Kim, Nicolas Sonnerat, Matej Balog, Gheorghe Comanici +13

IJCAI 2024poster

This work proposes a new learning-to-search benchmark and uses AI to discover new mathematical knowledge related to an open conjecture of Erdos (1975) in extremal graph theory. The problem is to find graphs with a given size (number of nodes) that maximize the number of edges without having 3- or 4-…

Cited by 7 Source ↗PDF ↗Scholar ↗

2019

The Option Keyboard: Combining Skills in Reinforcement Learning

Andre Barreto, Diana Borsa, Shaobo Hou, Gheorghe Comanici, Eser Aygün, Philippe Hamel +5

NeurIPS 2019poster

The ability to combine known skills to create new ones may be crucial in the solution of complex reinforcement learning problems that unfold over extended periods. We argue that a robust way of combining skills is to define and manipulate them in the space of pseudo-rewards (or "cumulants"). Based o…

Cited by 122 Source ↗PDF ↗Scholar ↗