Agent sensing with stateful resources

In the application of multi-agent systems to real-world problems, agents often suffer from bounded rationality where agent reasoning is limited by 1) a lack of knowledge about choices, and 2) a lack of resources required for reasoning. To overcome the former, the agent uses sensing to refine its knowledge. However, sensing can also require limited resources, leading to inaccurate environment modeling and poor decision making. In this paper, we consider a novel and difficult class of this problem where agents must use stateful resources during sensing, which we define as resources whose state-dependent behavior changes over time based on usage. Specifically, such sensing changes the state of a resource, and thus its behavior, producing a phenomenon where the sensing activity can and will distort its own outcome. We term this the Observer Effect after the similar phenomenon in the physical sciences. Given this effect, the agent faces a strategic tradeoff between satisfying the need for 1) knowledge refinement, and 2) avoiding corruption of knowledge due to distorted sensing outcomes. To address this tradeoff, we use active perception to select sensing activities and model activity selection as a Markov decision process (MDP) solved through reinforcement learning where an agent optimizes knowledge refinement while considering the state of the resource used during sensing.