An ad hoc team setting is one in which teammates must work together to obtain a common goal, but without any prior agreement regarding how to work together. In this abstract we present a role-based approach for ad hoc teamwork, in which each teammate is inferred to be following a specialized role that accomplishes a specific task or exhibits a particular behavior. In such cases, the role an ad hoc agent should select depends both on its own capabilities and on the roles currently selected by the other team members. We present methods for evaluating the influence of the ad hoc agent's role selection on the team's utility and we examine empirically how to select the best suited method for role assignment in a complex environment. Finally, we show that an appropriate assignment method can be determined from a limited amount of data and used successfully in similar new tasks that the team has not encountered before.

In multiagent team settings, the agents are often given a protocol for coordinating their actions. When such a protocol is not available, agents must engage in ad hoc teamwork to effectively cooperate with one another. A fully general ad hoc team agent needs to be capable of collaborating with a wide range of potential teammates on a varying set of joint tasks. This paper extends previous research in a new direction with the introduction of an efficient method for reasoning about the value of information.  Then, we show how previous theoretical results can aid ad hoc agents in a set of testbed pursuit domains.

Opponent modeling is a critical mechanism in repeated games. It allows a player to adapt its strategy in order to better respond to the presumed preferences of his opponents. We introduce a new modeling technique that adaptively balances exploitability and risk reduction. An opponent’s strategy is modeled with a set of possible strategies that contain the actual strategy with a high probability. The algorithm is safe as the expected payoff is above the minimax payoff with a high probability, and can exploit the opponents’ preferences when sufficient observations have been obtained. We apply them to normal-form games and stochastic games with a finite number of stages. The performance of the proposed approach is first demonstrated on repeated rock-paper-scissors games. Subsequently, the approach is evaluated in a human-robot table-tennis setting where the robot player learns to prepare to return a served ball. By modeling the human players, the robot chooses a forehand, backhand or middle preparation pose before they serve. The learned strategies can exploit the opponent’s preferences, leading to a higher rate of successful returns.

There are many diverse domains like academic collaboration, service industry, and movies, where a group of agents are involved in a set of activities through interactions or collaborations to create value. The end result of the value creation process is two pronged: firstly, there is a cumulative value created due to the interactions and secondly, a network that captures the pattern of historical interactions between the agents. In this paper we summarize our efforts towards design and analysis of value creation networks: 1) network representation of interactions and value creations, 2) identify contribution of a node based on values created from various activities, and 3) ranking nodes based on structural properties of interactions and the resulting values. To highlight the efficacy of our proposed algorithms, we present results on IMDB and services industry data.

Creating accurate computational models of human decision making is a vital step towards the realization of socially intelligent systems capable of both predicting and simulating human behavior. In modeling human decision making, a key factor is the psychological phenomenon known as "framing", in which the preferences of a decision maker change in response to contextual changes in decision problems. Existing approaches treat framing as a one-dimensional contextual influence based on the perception of outcomes as either gains or losses. However, empirical studies have shown that framing effects are much more multifaceted than one-dimensional views of framing suggest. To address this limitation, we propose an integrative approach to modeling framing which combines the psychological principles of cognitive appraisal theories and decision-theoretic notions of utility and probability. We show that this approach allows for both the identification and computation of the salient contextual factors in a decision as well as modeling how they ultimately affect the decision process. Furthermore, we show that our multi-dimensional, appraisal-based approach can account for framing effects identified in the empirical literature which cannot be addressed by one-dimensional theories, thereby promising more accurate models of human behavior.

The hypothesis is presented that "cognitive synergy" -- proactive and mutually-assistive feedback between different cognitive processes associated with different types of memory -- may serve as a foundation for advanced artificial general intelligence. A specific AI architecture founded on this idea, OpenCogPrime, is described, in the context of its application to control virtual agents and robots. The manifestations of cognitive synergy in OpenCogPrime's procedural and declarative learning algorithms are discussed in some detail.

In this paper, we propose a novel decentralised control mechanism to manage micro-storage in the smart grid. Our approach uses an adaptive pricing scheme that energy suppliers apply to home smart agents controlling micro-storage devices. In particular, we prove that the interaction between a supplier using our pricing scheme and the actions of selfish micro-storage agents forms a globally stable feedback loop that converges to an efficient equilibrium. We further propose a market strategy that allows the supplier to reduce wholesale purchasing costs without increasing the uncertainty and variance for its aggregate consumer demand. Moreover, we empirically evaluate our mechanism (based on the UK grid data) and show that it yields savings of up to 16% in energy cost for consumers using storage devices with average capacity 10 kWh. Furthermore, we show that it is robust against extreme system changes.

One proposed approach to managing a large complex Smart Grid is through Broker Agents who buy electrical power from distributed producers, and also sell power to consumers, via a Tariff Market--a new market mechanism where Broker Agents publish concurrent bid and ask prices. A key challenge is the specification of the market strategy that the Broker Agents should use in order to earn profits while maintaining the market's balance of supply and demand. Interestingly, previous work has shown that a Broker Agent can learn its strategy, using Markov Decision Processes (MDPs) and Q-learning, and outperform other Broker Agents that use predetermined or randomized strategies. In this work, we investigate the more representative scenario in which multiple Broker Agents, instead of a single one, are independently learning their strategies. Using a simulation environment based on real data, we find that Broker Agents who employ periodic increases in exploration achieve higher rewards. We also find that varying levels of market dominance in customer allocation models result in remarkably distinct outcomes in market prices and aggregate Broker Agent rewards. The latter set of results can be explained by established economic principles regarding the emergence of monopolies in market-based competition, further validating our approach.

Plants can have positive effects on each other in numerous ways, including protection from harsh environmental conditions. This phenomenon, known as facilitation, occurs in water-stressed environments when shade from larger shrubs protects smaller annuals from harsh sun, enabling them to exist on scarce water. The topic of this paper is a model of this phenomenon that allows search algorithms to find residential landscape designs that incorporate facilitation to conserve water. This model is based in botany; it captures the growth requirements of real plant species in a fitness function, but also includes a penalty term in that function that encourages facilitative interactions with other plants on the landscape. To evaluate the effectiveness of this approach, two search strategies--simulated annealing and agent-based search--were applied to models of different collections of simulated plant types and landscapes with different light distributions. These two search strategies produced landscape designs with different spatial distributions of the larger plants. All designs exhibited facilitation and lower water use than designs where facilitation was not included.

Looking ahead to the time when autonomous cars will be common, Dresner and Stone proposed a multiagent systems-based intersection control protocol called Autonomous Intersection Management (AIM). They showed that by leveraging the capacities of autonomous vehicles it is possible to dramatically reduce the time wasted in traffic, and therefore also fuel consumption and air pollution. The proposed protocol, however, handles reservation requests one at a time and does not prioritize reservations according to their relative priorities and waiting times, causing potentially large inequalities in granting reservations. For example, at an intersection between a main street and an alley, vehicles from the alley can take an excessively long time to get reservations to enter the intersection, causing a waste of time and fuel. The same is true in a network of intersections, in which gridlock may occur and cause traffic congestion. In this paper, we introduce the batch processing of reservations in AIM to enforce liveness properties in intersections and analyze the conditions under which no vehicle will get stuck in traffic. Our experimental results show that our prioritizing schemes outperform previous intersection control protocols in unbalanced traffic.