Gradient-free Online Learning in Games with Delayed Rewards
Abstract
Motivated by applications to online advertising and recommender systems, we consider a game-theoretic model with delayed rewards and asynchronous, payoff-based feedback. In contrast to previous work on delayed multi-armed bandits, we focus on multi-player games with continuous action spaces, and we examine the long-run behavior of strategic agents that follow a no-regret learning policy (but are otherwise oblivious to the game being played, the objectives of their opponents, etc.). To account for the lack of a consistent stream of information (for instance, rewards can arrive out of order, with an a priori unbounded delay, etc.), we introduce a gradient-free learning policy where payoff information is placed in a priority queue as it arrives. In this general context, we derive new bounds for the agents' regret; furthermore, under a standard diagonal concavity assumption, we show that the induced sequence of play converges to Nash equilibrium with probability , even if the delay between choosing an action and receiving the corresponding reward is unbounded.
Cite
@article{arxiv.2006.10911,
title = {Gradient-free Online Learning in Games with Delayed Rewards},
author = {Amélie Héliou and Panayotis Mertikopoulos and Zhengyuan Zhou},
journal= {arXiv preprint arXiv:2006.10911},
year = {2020}
}
Comments
26 pages, 4 figures; to appear in ICML 2020