Stochastic matrix games with bandit feedback

By Brendan O'Donoghue, Tor Lattimore, Ian Osband. 2020

8 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Brendan O'Donoghue
2. Sergey Levine
3. Ian Osband
4. Tuomas Haarnoja
5. Aviral Kumar
6. Tom Goldstein
7. Yuxi Li
8. Stephen P. Boyd

Citations in the corpus

• Variational Bayesian Reinforcement Learning with Regret Bounds (2018, background): “For one, it was recently shown that K-learning extends naturally to the case of two-player games and continues to enjoy a sub-linear regret bound, whereas Thompson sampling can suffer linear regret [34].”