A metareasoning problem involves three parts: 1) a set of concrete problem domains; 2) reasoners to reason about the problems; and, 3) metareasoners to reason about the reasoners. We believe that the metareasoning community would benefit from agreeing on the first two problems. To support this kind of collaboration, we offer an open source 3D simulator containing everyday, commonsense problems that take place in kitchens. This paper presents several arguments for using a simulator to solve commonsense problems. The paper concludes by describing future work in simulator-based unified generative benchmarks for AI.

Many approaches were explored in recent years to introduce principles of metacognition and meta-learning into cognitive architectures, yet none of them resulted in a scalable human-like learner. This work presents an approach intended to fill the gap between human self-regulated learners and artificial learners by introducing a new spin of the familiar core cognitive architecture paradigm, taking it to a meta-level. The resultant architecture enables in artifacts exclusively human higher cognitive and learning abilities: specifically, deliberative new knowledge construction. Model predictions agree with results of a pilot study with human subjects.

It is crucial for social systems to adapt to the dynamics of open environments. This adaptation process becomes especially challenging in the context of multiagent systems. In this paper, we argue that multiagent meta-level control is an effective way to determine when this adaptation process should be done and how much effort should be invested in adaptation as opposed to continuing with the current action plan. We develop a reinforcement learning based mechanism for multiagent meta-level control that facilitates the metalevel control component of each agent to learn policies in a decentralized fashion that (a) it can efficiently support agent interactions with other agents and (b) reorganize the underlying network when needed. We evaluate this mechanism in the context of a multiagent tornado tracking application called NetRads. Empirical results show that adaptive multiagent meta-level control significantly improves the performance of the tornado tracking network for a variety of weather scenarios.

One of the challenges of multiagent decision making is that the behavior needed to maximize utility can depend on what other agents choose to do: sometimes there is no "right" answer in the absence of knowledge of how opponents will act. The Nash equilibrium is a sensible choice of behavior because it represents a mutual best response. But, even when there is a unique equilibrium, other players are under no obligation to take part in it. This observation has been forcefully illustrated in the behavioral economics community where repeated experiments have shown individuals playing Nash equilibria and performing badly as a result. In this paper, we show how to apply a tool from behavioral economics called the Cognitive Hierarchy (CH) to the design of agents in general sum games. We attack the recently introduced ``Lemonade Game'' and show how the results of an open competition are well explained by CH. We believe this game, and perhaps many other similar games, boils down to predicting how deeply other agents in the game will be reasoning. An agent that does not reason enough risks being exploited by its opponents, while an agent that reasons too much may not be able to interact productively with its opponents. We demonstrate these ideas by presenting empirical results using agents from the competition and idealizations arising from a CH analysis.

Distributed Partially Observable Markov Decision Processes (DEC-POMDPs) are a popular planning framework for multiagent teamwork to compute (near-)optimal plans. However, these methods assume a complete and correct world model, which is often violated in real-world domains. We provide a new algorithm for DEC-POMDPs that is more robust to model uncertainty, with a focus on domains with sparse agent interactions. Our STC algorithm relies on the following key ideas: (1) reduce planning-time computation by shifting some of the burden to execution-time reasoning, (2) exploit sparse interactions between agents, and (3) maintain an approximate model of agents’ beliefs. We empirically show that STC is often substantially faster to existing DEC-POMDP methods without sacrificing reward performance.

We study several classes of interactive assistants from the points of view of decision theory and computational complexity. We first introduce a special class of POMDPs called hidden-goal MDPs (HGMDPs), which formalize the problem of interactively assisting an agent whose goal is hidden and whose actions are observable. In spite of its restricted nature, we show that optimal action selection in finite horizon HGMDPs is PSPACE-complete even in domains with deterministic dynamics. We then introduce a more restricted model called helper action MDPs (HAMDPs), where the assistant’s action is accepted by the agent when it is helpful, and can be easily ignored by the agent otherwise. We show classes of HAMDPs that are complete for PSPACE and NP along with a polynomial time class. Furthermore, we show that for general HAMDPs a simple myopic policy achieves a regret, compared to an omniscient assistant, that is bounded by the entropy of the initial goal distribution. A variation of this policy is also shown to achieve worst-case regret that is logarithmic in the number of goals for any goal distribution.

Mixed reality is an important classroom tool for managing complexity from both the students' and instructor's standpoints. It can be used to provide important scaffolds when introducing robotics, by allowing elements of perception and control to be abstracted, and these abstractions removed as a course progresses (or left in place to introduce robotics to younger groups of students). In prior work, we have illustrated the potential of this approach both in providing scaffolding, building an inexpensive robotics laboratory, and also providing control of evaluation of robotics environments for student evaluation and scientific experimentation. In this paper, we explore integrating extensions and improvements to the mixed reality components themselves as part of a course in applied artificial intelligence and robotics. We present a set of assignments that in addition to exploring robotics concepts, actively integrate creating or improving mixed reality components. We find that this approach better leverages the advantages brought about by mixed reality in terms of student motivation, and also provides some very useful software engineering experience to the students.

When agents are acting together, they may need a simple mechanism to decide on joint actions. One possibility is to have the agents express their preferences in the form of a ballot and use a voting rule to decide the winning action(s). Unfortunately, agents may try to manipulate such an election by misreporting their preferences. Fortunately, it has been shown that it is NP-hard to compute how to manipulate a number of different voting rules. However, NP-hardness only bounds the worst-case complexity. Recent theoretical results suggest that manipulation may often be easy in practice. To address this issue, I suggest studying empirically if computational complexity is in practice a barrier to manipulation. The basic tool used in my investigations is the identification of computational "phase transitions". Such an approach has been fruitful in identifying hard instances of propositional satisfiability and other NP-hard problems. I show that phase transition behaviour gives insight into the hardness of manipulating voting rules, increasing concern that computational complexity is indeed any sort of barrier. Finally, I look at the problem of computing manipulation of other, related problems like stable marriage and tournament problems.

PIM: A Novel Architecture for Coordinating Behavior of Distributed Systems

Applying Software Engineering to Agent Development