基础算法概述
Double Oracle (DO) and PSRO approximate Nash equilibria in two-player zero-sum games by iteratively expanding a strategy population with best responses supplied by an oracle. Online Double Oracle (ODO) interleaves multiplicative weights updates (MWU) with population discovery and obtains an $O(\sqrt{k\ln k/T})$ rate, where $T$ is the number of learning rounds and $k$ is the larger of the two players' final population sizes.
现有方法的设计短板
We identify the reinitialisation step as an underexplored design choice: at each expansion, MWU-based methods reset newly discovered strategies to a uniform prior.
Virtual Double Oracle(VDO)的提出与理论保证
We introduce Virtual Double Oracle (VDO), which exploits a bilinear identity (a strategy's full hindsight loss history collapses to its utility against the time-averaged opponent) to initialise each new strategy with the MWU weight it would have had from the start.
We prove that VDO achieves $O(\sqrt{k/T})$ exploitability over the discovered population as it grows, provided the cumulative cost of adding strategies is at most linear in $k$, a condition supported by our empirical measurements.
Discounted VDO(dVDO)的优化改进
Discounted VDO (dVDO) moderates historical preferences to reduce over-concentration at reinitialisation.
实验验证结果
Experiments across matrix games, poker, and Goofspiel show that, with a suitable discount, dVDO can substantially reduce finite-horizon exploitability relative to both VDO and uniform-reset ODO, and can improve the discovered strategy populations.