We study the problem of learning a policy in a Markov decision process (MDP) based on observations of the actions taken by multiple teachers. We assume that the teachers are like-minded in that their reward functions -- while different from each other -- are random perturbations of an underlying reward function. Under this assumption, we demonstrate that inverse reinforcement learning algorithms that satisfy a certain property -- that of matching feature expectations -- yield policies that are approximately optimal with respect to the underlying reward function, and that no algorithm can do better in the worst case. We also show how to efficiently recover the optimal policy when the MDP has one state -- a setting that is akin to multi-armed bandits.

It is common to see a handful of reviewers reject a highly novel paper, because they view, say, extensive experiments as far more important than novelty, whereas the community as a whole would have embraced the paper. More generally, the disparate mapping of criteria scores to final recommendations by different reviewers is a major source of inconsistency in peer review. In this paper we present a framework inspired by empirical risk minimization (ERM) for learning the community's aggregate mapping. The key challenge that arises is the specification of a loss function for ERM. We consider the class of L(p,q) loss functions, which is a matrix-extension of the standard class of Lp losses on vectors; here the choice of the loss function amounts to choosing the hyperparameters p and q. To deal with the absence of ground truth in our problem, we instead draw on computational social choice to identify desirable values of the hyperparameters p and q. Specifically, we characterize p=q=1 as the only choice of these hyperparameters that satisfies three natural axiomatic properties. Finally, we implement and apply our approach to reviews from IJCAI 2017.

To be well-behaved, systems that process preference data must satisfy certain conditions identified by economic decision theory and by social choice theory. In ML, preferences and rankings are commonly learned by fitting a probabilistic model to noisy preference data. The behavior of this learning process from the view of economic theory has previously been studied for the case where the data consists of rankings. In practice, it is more common to have only pairwise comparison data, and the formal properties of the associated learning problem are more challenging to analyze. We show that a large class of random utility models (including the Thurstone–Mosteller Model), when estimated using the MLE, satisfy a Pareto efficiency condition. These models also satisfy a strong monotonicity property, which implies that the learning process is responsive to input data. On the other hand, we show that these models fail certain other consistency conditions from social choice theory, and in particular do not always follow the majority opinion. Our results inform existing and future applications of random utility models for societal decision making.

Virtual democracy is an approach to automating decisions, by learning models of the preferences of individual people, and, at runtime, aggregating the predicted preferences of those people on the dilemma at hand. One of the key questions is which aggregation method – or voting rule – to use; we offer a novel statistical viewpoint that provides guidance. Specifically, we seek voting rules that are robust to prediction errors, in that their output on people’s true preferences is likely to coincide with their output on noisy estimates thereof. We prove that the classic Borda count rule is robust in this sense, whereas any voting rule belonging to the wide family of pairwise-majority consistent rules is not. Our empirical results further support, and more precisely measure, the robustness of Borda count.

Autonomous cyber-physical agents play an increasingly large role in our lives. To ensure that they behave in ways aligned with the values of society, we must develop techniques that allow these agents to not only maximize their reward in an environment, but also to learn and follow the implicit constraints of society. We detail a novel approach that uses inverse reinforcement learning to learn a set of unspecified constraints from demonstrations and reinforcement learning to learn to maximize environmental rewards. A contextual bandit-based orchestrator then picks between the two policies: constraint-based and environment reward-based. The contextual bandit orchestrator allows the agent to mix policies in novel ways, taking the best actions from either a reward-maximizing or constrained policy. In addition, the orchestrator is transparent on which policy is being employed at each time step. We test our algorithms using Pac-Man and show that the agent is able to learn to act optimally, act within the demonstrated constraints, and mix these two functions in complex ways.

In classic fair division problems such as cake cutting and rent division, envy-freeness requires that each individual (weakly) prefer his allocation to anyone else's. On a conceptual level, we argue that envy-freeness also provides a compelling notion of fairness for classification tasks, especially when individuals have heterogeneous preferences. Our technical focus is the generalizability of envy-free classification, i.e., understanding whether a classifier that is envy free on a sample would be almost envy free with respect to the underlying distribution with high probability. Our main result establishes that a small sample is sufficient to achieve such guarantees, when the classifier in question is a mixture of deterministic classifiers that belong to a family of low Natarajan dimension.

Algorithms increasingly govern societal functions, impacting multiple stakeholders and social groups. How can we design these algorithms to balance varying interests in a moral, legitimate way? As one answer to this question, we present WeBuildAI, a collective participatory framework that enables people to build algorithmic policy for their communities. The key idea of the framework is to enable stakeholders to construct a computational model that represents their views and to have those models vote on their behalf to create algorithmic policy. As a case study, we applied this framework to a matching algorithm that operates an on-demand food donation transportation service in order to adjudicate equity and efficiency trade-offs. The service's stakeholders--donors, volunteers, recipient organizations, and nonprofit employees--used the framework to design the algorithm through a series of studies in which we researched their experiences. Our findings suggest that the framework successfully enabled participants to build models that they felt confident represented their own beliefs. Participatory algorithm design also improved both procedural fairness and the distributive outcomes of the algorithm, raised participants' algorithmic awareness, and helped identify inconsistencies in human decision-making in the governing organization. Our work demonstrates the feasibility, potential and challenges of community involvement in algorithm design.

Voting systems typically treat all voters equally. We argue that perhaps they should not: Voters who have supported good choices in the past should be given higher weight than voters who have supported bad ones. To develop a formal framework for desirable weighting schemes, we draw on no-regret learning. Specifically, given a voting rule, we wish to design a weighting scheme such that applying the voting rule, with voters weighted by the scheme, leads to choices that are almost as good as those endorsed by the best voter in hindsight. We derive possibility and impossibility results for the existence of such weighting schemes, depending on whether the voting rule and the weighting scheme are deterministic or randomized, as well as on the social choice axioms satisfied by the voting rule.

We present a general approach to automating ethical decisions, drawing on machine learning and computational social choice. In a nutshell, we propose to learn a model of societal preferences, and, when faced with a specific ethical dilemma at runtime, efficiently aggregate those preferences to identify a desirable choice. We provide a concrete algorithm that instantiates our approach; some of its crucial steps are informed by a new theory of swap-dominance efficient voting rules. Finally, we implement and evaluate a system for ethical decision making in the autonomous vehicle domain, using preference data collected from 1.3 million people through the Moral Machine website.

Lifted inference algorithms commonly exploit symmetries in a probabilistic graphical model (PGM) for efficient inference. However, existing algorithms for Boolean-valued domains can identify only those pairs of states as symmetric, in which the number of ones and zeros match exactly (count symmetries). Moreover, algorithms for lifted inference in multi-valued domains also compute a multi-valued extension of count symmetries only. These algorithms miss many symmetries in a domain. In this paper, we present first algorithms to compute non-count symmetries in both Boolean-valued and multi-valued domains. Our methods can also find symmetries between multi-valued variables that have different domain cardinalities. The key insight in the algorithms is that they change the unit of symmetry computation from a variable to a variable-value (VV) pair. Our experiments find that exploiting these symmetries in MCMC can obtain substantial computational gains over existing algorithms.