Though substantial research has been dedicated towards using technology to improve education, no current methods are as effective as one-on-one tutoring. A critical, though relatively understudied, aspect of effective tutoring is modulating the student's affective state throughout the tutoring session in order to maximize long-term learning gains. We developed an integrated experimental paradigm in which children play a second-language learning game on a tablet, in collaboration with a fully autonomous social robotic learning companion. As part of the system, we measured children's valence and engagement via an automatic facial expression analysis system. These signals were combined into a reward signal that fed into the robot's affective reinforcement learning algorithm. Over several sessions, the robot played the game and personalized its motivational strategies (using verbal and non-verbal actions) to each student. We evaluated this system with 34 children in preschool classrooms for a duration of two months. We saw that (1) children learned new words from the repeated tutoring sessions, (2) the affective policy personalized to students over the duration of the study, and (3) students who interacted with a robot that personalized its affective feedback strategy showed a significant increase in valence, as compared to students who interacted with a non-personalizing robot. This integrated system of tablet-based educational content, affective sensing, affective policy learning, and an autonomous social robot holds great promise for a more comprehensive approach to personalized tutoring.

In cooperative multi-agent sequential decision making under uncertainty, agents must coordinate to find an optimal joint policy that maximises joint value. Typical algorithms exploit additive structure in the value function, but in the fully-observable multi-agent MDP (MMDP) setting such structure is not present. We propose a new optimal solver for transition-independent MMDPs, in which agents can only affect their own state but their reward depends on joint transitions. We represent these dependencies compactly in conditional return graphs (CRGs). Using CRGs the value of a joint policy and the bounds on partially specified joint policies can be efficiently computed. We propose CoRe, a novel branch-and-bound policy search algorithm building on CRGs. CoRe typically requires less runtime than available alternatives and finds solutions to previously unsolvable problems.

This paper considers a mechanism design problem for locating two identical facilities on an interval, in which an agent can pretend to be multiple agents. A mechanism selects a pair of locations on the interval according to the declared single-peaked preferences of agents. An agent's utility is determined by the location of the better one (typically the closer to her ideal point). This model can represent various application domains. For example, assume a company is going to release two models of its product line and performs a questionnaire survey in an online forum to determine their detailed specs. Typically, a customer will buy only one model, but she can answer multiple times by logging onto the forum under several email accounts. We first characterize possible outcomes of mechanisms that satisfy false-name-proofness, as well as some mild conditions. By extending the result, we completely characterize the class of false-name-proof mechanisms when locating two facilities on a circle. We then clarify the approximation ratios of the false-name-proof mechanisms on a line metric for the social and maximum costs.

Many real world security problems can be modelled as finite zero-sum games with structured sequential strategies and limited interactions between the players. An abstract class of games unifying these models are the normal-form games with sequential strategies (NFGSS). We show that all games from this class can be modelled as well-formed imperfect-recall extensive-form games and consequently can be solved by counterfactual regret minimization. We propose an adaptation of the CFR+ algorithm for NFGSS and compare its performance to the standard methods based on linear programming and incremental game generation. We validate our approach on two security-inspired domains. We show that with a negligible loss in precision, CFR+ can compute a Nash equilibrium with five times less computation than its competitors.

Evolutionary game theory provides the principal tools to model the dynamics of multi-agent learning algorithms. While there is a long-standing literature on evolutionary game theory in strategic-form games, in the case of extensive-form games few results are known and the exponential size of the representations currently adopted makes the evolutionary analysis of such games unaffordable. In this paper, we focus on dynamics for the sequence form of extensive-form games, providing three dynamics: one realization equivalent to the normal-form logit dynamic, one realization equivalent to the agent-form replicator dynamic, and one realization equivalent to the agent-form logit dynamic. All the considered dynamics require polynomial time and space, providing an exponential compression w.r.t. the dynamics currently known and providing thus tools that can be effectively employed in practice. Moreover, we use our tools to compare the agent-form and normal-form dynamics and to provide new "hybrid" dynamics.

Counterfactual Regret Minimization (CFR) is a popular iterative algorithm for approximating Nash equilibria in imperfect-information multi-step two-player zero-sum games. We introduce the first general, principled method for warm starting CFR. Our approach requires only a strategy for each player, and accomplishes the warm start at the cost of a single traversal of the game tree. The method provably warm starts CFR to as many iterations as it would have taken to reach a strategy profile of the same quality as the input strategies, and does not alter the convergence bounds of the algorithms. Unlike prior approaches to warm starting, ours can be applied in all cases. Our method is agnostic to the origins of the input strategies. For example, they can be based on human domain knowledge, the observed strategy of a strong agent, the solution of a coarser abstraction, or the output of some algorithm that converges rapidly at first but slowly as it gets closer to an equilibrium. Experiments demonstrate that one can improve overall convergence in a game by first running CFR on a smaller, coarser abstraction of the game and then using the strategy in the abstract game to warm start CFR in the full game.

We present SVVAMP, a Python package dedicated to the study of voting systems with an emphasis on manipulation analysis.

We characterize the class of committee scoring rules that satisfy the fixed-majority criterion. In some sense, the committee scoring rules in this class are multiwinner analogues of the single-winner Plurality rule, which is uniquely characterized as the only single-winner scoring rule that satisfies the simple majority criterion. We find that, for most of the rules in our new class, the complexity of winner determination is high (i.e., the problem of computing the winners is NP-hard), but we also show some examples of polynomial-time winner determination procedures, exact and approximate.

In crowded multi-agent navigation environments, the motion of the agents is significantly constrained by the motion of the nearby agents. This makes planning paths very difficult and leads to inefficient global motion. To address this problem, we propose a new distributed approach to coordinate the motions of agents in crowded environments. With our approach, agents take into account the velocities and goals of their neighbors and optimize their motion accordingly and in real-time. We experimentally validate our coordination approach in a variety of scenarios and show that its performance scales to scenarios with hundreds of agents.

The leading approach to solving large imperfect information games is to pre-calculate an approximate solution using a simplified abstraction of the full game; that solution is then used to play the original, full-scale game. The abstraction step is necessitated by the size of the game tree. However, as the original game progresses, the remaining portion of the tree (the subgame) becomes smaller. An appealing idea is to use the simplified abstraction to play the early parts of the game and then, once the subgame becomes tractable, to calculate a solution using a finer-grained abstraction in real time, creating a combined final strategy. While this approach is straightforward for perfect information games, it is a much more complex problem for imperfect information games. If the subgame is solved locally, the opponent can alter his play in prior to this subgame to exploit our combined strategy. To prevent this, we introduce the notion of subgame margin, a simple value with appealing properties. If any best response reaches the subgame, the improvement of exploitability of the combined strategy is (at least) proportional to the subgame margin. This motivates subgame refinements resulting in large positive margins. Unfortunately, current techniques either neglect subgame margin (potentially leading to a large negative subgame margin and drastically more exploitable strategies), or guarantee only non-negative subgame margin (possibly producing the original, unrefined strategy, even if much stronger strategies are possible). Our technique remedies this problem by maximizing the subgame margin and is guaranteed to find the optimal solution. We evaluate our technique using one of the top participants of the AAAI-14 Computer Poker Competition, the leading playground for agents in imperfect information setting