具有私有状态的自利主体间的最优协调规划
Optimal Coordinated Planning Amongst Self-Interested Agents with Private State
摘要：
考虑一个处于动态和不确定环境中的多智能体系统。每个代理的局部决策问题被建模为马尔可夫决策过程（MDP）和代理必须协调在每个时期的联合行动，这提供了一个奖励给每个代理，并导致局部状态转换。社会规划者知道每个Agent的MDP模型，并希望执行最优联合策略，但Agent是自私的，具有私有的局部状态。我们提供了一个激励兼容的机制，用于引出状态信息，实现最佳的联合计划，在马尔可夫完美均衡的诱导随机游戏。在特殊情况下，局部问题是马尔可夫链和代理竞争采取单一的行动，在每个时期，我们利用Gittins分配指数提供一个有效的分解算法和分配计算的最优策略之间的代理。分布式，最佳的协调学习的多智能体变体的多臂强盗问题作为一个特例。
英文摘要：
Consider a multi-agent system in a dynamic and uncertain environment. Each agent's local decision problem is modeled as a Markov decision process (MDP) and agents must coordinate on a joint action in each period, which provides a reward to each agent and causes local state transitions. A social planner knows the model of every agent's MDP and wants to implement the optimal joint policy, but agents are self-interested and have private local state. We provide an incentive-compatible mechanism for eliciting state information that achieves the optimal joint plan in a Markov perfect equilibrium of the induced stochastic game. In the special case in which local problems are Markov chains and agents compete to take a single action in each period, we leverage Gittins allocation indices to provide an efficient factored algorithm and distribute computation of the optimal policy among the agents. Distributed, optimal coordinated learning in a multi-agent variant of the multi-armed bandit problem is obtained as a special case.
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。
