A Reduction-based Framework for Sequential Decision Making with Delayed Feedback
This work addresses delays in sequential decision making for multi-agent systems, offering a general framework that is incremental but extends to new areas like function approximation.
The authors tackled the problem of stochastic delayed feedback in multi-agent sequential decision making, including bandits, MDPs, and Markov games, by proposing a reduction-based framework that converts algorithms for instantaneous feedback into sample-efficient ones for delayed settings, achieving results that match or improve existing ones and providing the first studies with function approximation.
We study stochastic delayed feedback in general multi-agent sequential decision making, which includes bandits, single-agent Markov decision processes (MDPs), and Markov games (MGs). We propose a novel reduction-based framework, which turns any multi-batched algorithm for sequential decision making with instantaneous feedback into a sample-efficient algorithm that can handle stochastic delays in sequential decision making. By plugging different multi-batched algorithms into our framework, we provide several examples demonstrating that our framework not only matches or improves existing results for bandits, tabular MDPs, and tabular MGs, but also provides the first line of studies on delays in sequential decision making with function approximation. In summary, we provide a complete set of sharp results for multi-agent sequential decision making with delayed feedback.