Instance-dependent sample complexity for zero-sum matrix games
Characterize, game by game, how many noisy payoff samples it takes to find a near-equilibrium of a zero-sum matrix game.
PR
PR 把工作从一条路线带到另一条;合并它就是采纳。
没有开放的 PR
PR 把工作从一个分支带到另一个分支。
Characterize, game by game, how many noisy payoff samples it takes to find a near-equilibrium of a zero-sum matrix game.
PR 把工作从一条路线带到另一条;合并它就是采纳。
PR 把工作从一个分支带到另一个分支。