There has been tremendous recent progress on equilibrium-finding algorithms for zero-sum imperfect-information extensive-form games, but there has been a puzzling gap between theory and practice. First-order methods have significantly better theoretical convergence rates than any counterfactual-regret minimization (CFR) variant. Despite this, CFR variants have been favored in practice. Experiments with first-order methods have only been conducted on small- and medium-sized games because those methods are complicated to implement in this setting, and because CFR variants have been enhanced extensively for over a decade they perform well in practice. In this paper we show that a particular first-order method, a state-of-the-art variant of the excessive gap technique---instantiated with the dilated entropy distance function---can efficiently solve large real-world problems competitively with CFR and its variants. We show this on large endgames encountered by the Libratus poker AI, which recently beat top human poker specialist professionals at no-limit Texas hold'em. We show experimental results on our variant of the excessive gap technique as well as a prior version. We introduce a numerically friendly implementation of the smoothed best response computation associated with first-order methods for extensive-form game solving. We present, to our knowledge, the first GPU implementation of a first-order method for extensive-form games. We present comparisons of several excessive gap technique and CFR variants.

Abstraction has long been a key component in the practical solving of large-scale extensive-form games. Despite this, abstraction remains poorly understood. There have been some recent theoretical results but they have been confined to specific assumptions on abstraction structure and are specific to various disjoint types of abstraction, and specific solution concepts, for example, exact Nash equilibria or strategies with bounded immediate regret. In this paper we present a unified framework for analyzing abstractions that can express all types of abstractions and solution concepts used in prior papers with performance guarantees---while maintaining comparable bounds on abstraction quality. Moreover, our framework gives an exact decomposition of abstraction error in a much broader class of games, albeit only in an ex-post sense, as our results depend on the specific strategy chosen. Nonetheless, we use this ex-post decomposition along with slightly weaker assumptions than prior work to derive generalizations of prior bounds on abstraction quality. We also show, via counterexample, that such assumptions are necessary for some games. Finally, we prove the first bounds for how $\epsilon$-Nash equilibria computed in abstractions perform in the original game. This is important because often one cannot afford to compute an exact Nash equilibrium in the abstraction. All our results apply to general-sum n-player games.

Today, we see chatbots that augment the work of support agents by pre-filtering customer queries. We use this type of technology with our own Customer Success team, and we've found it's been hugely effective in helping them focus on the most complicated cases and deeper customer interactions. Then there are intelligent agents; these are fully autonomous agents who take over low value, rote, repetitive tasks. Over the past two decades, as we've fully digitized the workplace, these tasks have devolved onto knowledge workers, stealing precious time from the jobs they were actually hired to do. Think of things like expense reporting, travel booking, and meeting scheduling.

A key issue in cooperative game theory is coalitional stability, usually captured by the notion of the core---the set of outcomes that are resistant to group deviations. However, some coalitional games have empty cores, and any outcome in such a game is unstable. We investigate the possibility of stabilizing a coalitional game by using subsidies. We consider scenarios where an external party that is interested in having the players work together offers a supplemental payment to the grand coalition, or, more generally, a particular coalition structure. This payment is conditional on players not deviating from this coalition structure, and may be divided among the players in any way they wish. We define the cost of stability as the minimum external payment that stabilizes the game. We provide tight bounds on the cost of stability, both for games where the coalitional values are nonnegative (profit-sharing games) and for games where the coalitional values are nonpositive (cost-sharing games), under natural assumptions on the characteristic function, such as superadditivity, anonymity, or both. We also investigate the relationship between the cost of stability and several variants of the least core. Finally, we study the computational complexity of problems related to the cost of stability, with a focus on weighted voting games.

In the multi-agent path finding problem (MAPF) we are given a set of agents each with respective start and goal positions. The task is to find paths for all agents while avoiding collisions aiming to minimize an objective function. Two such common objective functions is the sum-of-costs and the makespan. Many optimal solvers were introduced in the past decade - two prominent categories of solvers can be distinguished: search-based solvers and compilation-based solvers. Search-based solvers were developed and tested for the sum-of-costs objective while the most prominent compilation-based solvers that are built around Boolean satisfiability (SAT) were designed for the makespan objective. Very little was known on the performance and relevance of the compilation-based approach on the sum-of-costs objective. In this paper we show how to close the gap between these cost functions in the compilation-based approach. Moreover we study applicability of various techniques developed for search-based solvers in the compilation-based approach. A part of this paper introduces a SAT-solver that is directly aimed to solve the sum-of-costs objective function. Using both a lower bound on the sum-of-costs and an upper bound on the makespan, we are able to have a reasonable number of variables in our SAT encoding. We then further improve the encoding by borrowing ideas from ICTS, a search-based solver. Experimental evaluation on several domains show that there are many scenarios where our new SAT-based methods outperforms the best variants of previous sum-of-costs search solvers - the ICTS, CBS algorithms, and ICBS algorithms.

In important applications involving multi-task networks with multiple objectives, agents in the network need to decide between these multiple objectives and reach an agreement about which single objective to follow for the network. In this work we propose a distributed decision-making algorithm. The agents are assumed to observe data that may be generated by different models. Through localized interactions, the agents reach agreement about which model to track and interact with each other in order to enhance the network performance. We investigate the approach for both static and mobile networks. The simulations illustrate the performance of the proposed strategies.

Learning when to communicate and doing that effectively is essential in multi-agent tasks. Recent works show that continuous communication allows efficient training with back-propagation in multi-agent scenarios, but have been restricted to fully-cooperative tasks. In this paper, we present Individualized Controlled Continuous Communication Model (IC3Net) which has better training efficiency than simple continuous communication model, and can be applied to semi-cooperative and competitive settings along with the cooperative settings. IC3Net controls continuous communication with a gating mechanism and uses individualized rewards foreach agent to gain better performance and scalability while fixing credit assignment issues. Using variety of tasks including StarCraft BroodWars explore and combat scenarios, we show that our network yields improved performance and convergence rates than the baselines as the scale increases. Our results convey that IC3Net agents learn when to communicate based on the scenario and profitability.

If artificial intelligence (AI) agents are to become real players in society, using their machine abilities to complement our human strengths, they must first become players in the video game of Minecraft. And to prove themselves in Minecraft, they must work together to capture animals in a maze, build towers of blocks, and hunt for treasure while fighting off skeletons. That, anyway, is the premise of a competition organized by Microsoft, Queen Mary University of London, and crowdAI (a platform for data-science challenges). Next month, the organizers will announce the winner--the team that created an AI that could best observe its Minecraft environment, determine which of three missions it had to accomplish, and then collaborate with another AI agent to carry out that mission. By emphasizing adaptability and cooperation, the organizers aimed to encourage research on AI agents that could one day interact with humans to accomplish tasks in the real world.

Natural, social, and artificial multi-agent systems usually operate in dynamic environments, where the ability to respond to changing circumstances is a crucial feature. An effective collective response requires suitable information transfer among agents, and thus is critically dependent on the agents' interaction network. In order to investigate the influence of the network topology on collective response, we consider an archetypal model of distributed decision-making---the leader-follower linear consensus---and study the collective capacity of the system to follow a dynamic driving signal (the "leader") for a range of topologies and system sizes. The analysis reveals a nontrivial relationship between optimal topology and frequency of the driving signal. Interestingly, the response is optimal when each individual interacts with a certain number of agents which decreases monotonically with the frequency and, for large enough systems, is independent of the size of the system. This phenomenology is investigated in experiments of collective motion using a swarm of land robots. The emergent collective response to both a slow- and a fast-changing leader is measured and analyzed for a range of interaction topologies. These results have far-reaching practical implications for the design and understanding of distributed systems, since they highlight that a dynamic rewiring of the interaction network is paramount to the effective collective operations of multi-agent systems at different time-scales.

Artificial Intelligence (AI) technologies could be broadly categorised into Analytics and Autonomy. Analytics focuses on algorithms offering perception, comprehension, and projection of knowledge gleaned from sensorial data. Autonomy revolves around decision making, and influencing and shaping the environment through action production. A smart autonomous system (SAS) combines analytics and autonomy to understand, learn, decide and act autonomously. To be useful, SAS must be trusted and that requires testing. Lifelong learning of a SAS compounds the testing process. In the remote chance that it is possible to fully test and certify the system pre-release, which is theoretically an undecidable problem, it is near impossible to predict the future behaviours that these systems, alone or collectively, will exhibit. While it may be feasible to severely restrict such systems\textquoteright \ learning abilities to limit the potential unpredictability of their behaviours, an undesirable consequence may be severely limiting their utility. In this paper, we propose the architecture for a watchdog AI (WAI) agent dedicated to lifelong functional testing of SAS. We further propose system specifications including a level of abstraction whereby humans shepherd a swarm of WAI agents to oversee an ecosystem made of humans and SAS. The discussion extends to the challenges, pros, and cons of the proposed concept.