Corpus ID: 219558780

Stochastic matrix games with bandit feedback

@article{ODonoghue2020StochasticMG,
  title={Stochastic matrix games with bandit feedback},
  author={Brendan O'Donoghue and Tor Lattimore and Ian Osband},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.05145}
}
We study a version of the classical zero-sum matrix game with unknown payoff matrix and bandit feedback, where the players only observe each others actions and a noisy payoff. This generalizes the usual matrix game, where the payoff matrix is known to the players. Despite numerous applications, this problem has received relatively little attention. Although adversarial bandit algorithms achieve low regret, they do not exploit the matrix structure and perform poorly relative to the new… Expand

References

SHOWING 1-10 OF 46 REFERENCES
Optimization, Learning, and Games with Predictable Sequences
  • 157
  • PDF
Gambling in a rigged casino: The adversarial multi-armed bandit problem
  • 741
  • PDF
The Nonstochastic Multiarmed Bandit Problem
  • 1,683
  • PDF
Adversarial Bandits with Knapsacks
  • 21
  • PDF
More Adaptive Algorithms for Adversarial Bandits
  • 48
  • PDF
Partial Monitoring - Classification, Regret Bounds, and Algorithms
  • 88
  • PDF
Efficient learning by implicit exploration in bandit problems with side observations
  • 63
  • PDF
Finite-time Analysis of the Multiarmed Bandit Problem
  • 4,458
  • PDF
Minimizing Regret : The General Case
  • 63
  • PDF
Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems
  • 1,729
  • PDF
...
1
2
3
4
5
...