无折扣的强盗游戏
Undiscounted Bandit Games
摘要:
我们分析了两个武装土匪的战略实验的非折扣连续时间游戏。风险臂根据Lévy过程产生收益,单位时间的平均收益未知,自然界从任意有限集合中得出。观察所有的行动和实现的收益,加上一个自由的背景信号,球员使用马尔可夫策略与共同的后验信念的未知参数作为状态变量。我们发现,唯一的对称马尔可夫完美均衡可以计算在一个简单的封闭的形式,只涉及安全臂的回报,预期的风险臂的当前回报,和预期的全信息回报,给定当前的信念。特别是,均衡并不依赖于收益产生过程的精确规范。
英文摘要:
We analyze undiscounted continuous-time games of strategic experimentation with two-armed bandits. The risky arm generates payoffs according to a Lévy process with an unknown average payoff per unit of time which nature draws from an arbitrary finite set. Observing all actions and realized payoffs, plus a free background signal, players use Markov strategies with the common posterior belief about the unknown parameter as the state variable. We show that the unique symmetric Markov perfect equilibrium can be computed in a simple closed form involving only the payoff of the safe arm, the expected current payoff of the risky arm, and the expected full-information payoff, given the current belief. In particular, the equilibrium does not depend on the precise specification of the payoff-generating processes.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。