Open agent systems are prevalent in the real world, where the sets of agents and tasks change over time. In this paper, we focus on task-open multi-agent systems, exemplified by applications such as ridesharing, where passengers (tasks) appear spontaneously over time and disappear if not attended to promptly. Task-open settings challenge us with an action space which changes dynamically. This renders existing reinforcement learning (RL) methods–intended for fixed state and action spaces–inapplicable. Whereas multi-task learning approaches learn policies generalized to multiple known and related tasks, they struggle to adapt to previously unseen tasks. Conversely, lifelong learning adapts to new tasks over time, but generally assumes that tasks come sequentially from a static and known distribution rather than simultaneously and unpredictably. We introduce a novel category of RL for addressing task openness, modeled using a task-open Markov game. Our approach, MOHITO, is a multi-agent actor-critic schema which represents knowledge about the relationships between agents and changing tasks and actions as dynamically evolving 3-uniform hypergraphs. As popular multi-agent RL testbeds do not exhibit task openness, we evaluate MOHITO on two realistic and naturally task-open domains to establish its efficacy and provide a benchmark for future work in this setting.

Rotating savings and credit associations (roscas) are informal financial organizations common in settings where communities have reduced access to formal financial institutions. In a rosca, a fixed group of participants regularly contribute sums of money to a pot. This pot is then allocated periodically using lottery, aftermarket, or auction mechanisms. Roscas are empirically well-studied in economics. They are, however, challenging to study theoretically due to their dynamic nature. Typical economic analyses of roscas stop at coarse ordinal welfare comparisons to other credit allocation mechanisms, leaving much of roscas' ubiquity unexplained. In this work, we take an algorithmic perspective on the study of roscas. Building on techniques from the price of anarchy literature, we present worst-case welfare approximation guarantees. We further experimentally compare the welfare of outcomes as key features of the environment vary. These cardinal welfare analyses further rationalize the prevalence of roscas. We conclude by discussing several other promising avenues.

In open multiagent systems, the set of agents operating in the environment changes over time and in ways that are nontrivial to predict. For example, if collaborative robots were tasked with fighting wildfires, they may run out of suppressants and be temporarily unavailable to assist their peers. Because an agent’s optimal action depends on the actions of others, each agent must not only predict the actions of its peers, but, before that, reason whether they are even present to perform an action. Addressing openness thus requires agents to model each other’s presence, which can be enhanced through agents communicating about their presence in the environment. At the same time, communicative acts can also incur costs (e.g., consuming limited bandwidth), and thus an agent must tradeoff the benefits of enhanced coordination with the costs of communication. We present a new principled, decision-theoretic method in the context provided by the recent communicative interactive POMDP framework for planning in open agent settings that balances this tradeoff. Simulations of multiagent wildfire suppression problems demonstrate how communication can improve planning in open agent environments, as well as how agents tradeoff the benefits and costs of communication under different scenarios.

In open agent systems, the set of agents that are cooperating or competing changes over time and in ways that are nontrivial to predict. For example, if collaborative robots were tasked with fighting wildfires, they may run out of suppressants and be temporarily unavailable to assist their peers. We consider the problem of planning in these contexts with the additional challenges that the agents are unable to communicate with each other and that there are many of them. Because an agent's optimal action depends on the actions of others, each agent must not only predict the actions of its peers, but, before that, reason whether they are even present to perform an action. Addressing openness thus requires agents to model each other's presence, which becomes computationally intractable with high numbers of agents. We present a novel, principled, and scalable method in this context that enables an agent to reason about others' presence in its shared environment and their actions. Our method extrapolates models of a few peers to the overall behavior of the many-agent system, and combines it with a generalization of Monte Carlo tree search to perform individual agent reasoning in many-agent open environments. Theoretical analyses establish the number of agents to model in order to achieve acceptable worst case bounds on extrapolation error, as well as regret bounds on the agent's utility from modeling only some neighbors. Simulations of multiagent wildfire suppression problems demonstrate our approach's efficacy compared with alternative baselines.

Introductory computer science courses are being increasingly taught using technology-mediated instruction and e-learning environments. The software and technology in such courses could benefit from the use of student models to inform and guide customized support tailored to the needs of individual students. In this paper, we investigate how student motivated engagement profiles developed in educational research can be used as such models to predict student behaviors. These models are advantageous over those learned directly from observing individual students, as they rely on different data that can be available a priori before students use the technology. Using tracked behaviors of 249 students from 7 CS1 courses over the span of 3 semesters, we discover that students with different engagement profiles indeed behave differently in an online, wiki-based CSCL system while performing collaborative creative thinking exercises, and the differences between students are primarily as expected based on the differences in the profiles. Thus, such profiles could be useful as student models for providing customized support in e-learning environments in CS1 courses.