Basically, in (one-player) war Real Time Strategy (wRTS) games a human player controls, in real time, an army consisting of a number of soldiers and her aim is to destroy the opponent's assets where the opponent is a virtual (i.e., non-human player controlled) player that usually consists of a pre-programmed decision-making script. These scripts have usually associated some well-known problems (e.g., predictability, non-rationality, repetitive behaviors, and sensation of artificial stupidity among others). This paper describes a method for the automatic generation of virtual players that adapt to the player skills; this is done by building initially a model of the player behavior in real time during the game, and further evolving the virtual player via this model in-between two games. The paper also shows preliminary results obtained on a one player wRTS game constructed specifically for experimentation.

Modeling interaction with robots raises new and different challenges for dialog modeling than traditional dialog modeling with less embodied machines. We present four case studies of implementing a typical human-robot interaction scenario with different state-of-the-art dialog frameworks in order to identify challenges and pitfalls specific to HRI and potential solutions. The results are discussed with a special focus on the interplay between dialog and task modeling on robots.

Believability of characters has been an objective in literature, theater, film, and animation. We argue that believable robot characters are important in human-robot interaction, as well. In particular, we contend that believable characters evoke users’ social responses that, for some tasks, lead to more natural interactions and are associated with improved task performance. In a dialogue-capable robot, a key to such believability is the integration of a consistent storyline, verbal and nonverbal behaviors, and sociocultural context. We describe our work in this area and present empirical results from three robot receptionist testbeds that operate "in the wild."

Skill discovery algorithms in reinforcement learning typically identify single states or regions in state space that correspond to task-specific subgoals. However, such methods do not directly address the question of how many distinct skills are appropriate for solving the tasks that the agent faces. This can be highly inefficient when many identified subgoals correspond to the same underlying skill, but are all used individually as skill goals. Furthermore, skills created in this manner are often only transferable to tasks that share identical state spaces, since corresponding subgoals across tasks are not merged into a single skill goal. We show that these problems can be overcome by clustering subgoal data defined in an agent-space and using the resulting clusters as templates for skill termination conditions. Clustering via a Dirichlet process mixture model is used to discover a minimal, sufficient collection of portable skills.

Factored Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs) form a powerful framework for multiagent planning under uncertainty, but optimal solutions require a rigid history-based policy representation. In this paper we allow inter-agent communication which turns the problem in a centralized Multiagent POMDP (MPOMDP). We map belief distributions over state factors to an agent's local actions by exploiting structure in the joint MPOMDP policy. The key point is that when sparse dependencies between the agents' decisions exist, often the belief over its local state factors is sufficient for an agent to unequivocally identify the optimal action, and communication can be avoided. We formalize these notions by casting the problem into convex optimization form, and present experimental results illustrating the savings in communication that we can obtain.

We present a new algorithm for exactly solving decision-making problems represented as an influence diagram. We do not require the usual assumptions of no forgetting and regularity, which allows us to solve problems with limited information. The algorithm, which implements a sophisticated variable elimination procedure, is empirically shown to outperform a state-of-the-art algorithm in randomly generated problems of up to 150 variables and $10^{64}$ strategies.

We present a novel class of actor-critic algorithms for actors consisting of sets of interacting modules. We present, analyze theoretically, and empirically evaluate an update rule for each module, which requires only local information: the module's input, output, and the TD error broadcast by a critic. Such updates are necessary when computation of compatible features becomes prohibitively difficult and are also desirable to increase the biological plausibility of reinforcement learning methods.

The problem of adversarial multi-robot patrol has gained interest in recent years, mainly due to its immediate relevance to various security applications. In this problem, robots are required to repeatedly visit a target area in a way that maximizes their chances of detecting an adversary trying to penetrate through the patrol path. When facing a strong adversary that knows the patrol strategy of the robots, if the robots use a deterministic patrol algorithm, then in many cases it is easy for the adversary to penetrate undetected (in fact, in some of those cases the adversary can guarantee penetration). Therefore this paper presents a non-deterministic patrol framework for the robots. Assuming that the strong adversary will take advantage of its knowledge and try to penetrate through the patrol's weakest spot, hence an optimal algorithm is one that maximizes the chances of detection in that point. We therefore present a polynomial-time algorithm for determining an optimal patrol under the Markovian strategy assumption for the robots, such that the probability of detecting the adversary in the patrol's weakest spot is maximized. We build upon this framework and describe an optimal patrol strategy for several robotic models based on their movement abilities (directed or undirected) and sensing abilities (perfect or imperfect), and in different environment models - either patrol around a perimeter (closed polygon) or an open fence (open polyline).

In this paper, we present a novel decentralised management technique that allows electricity micro-storage devices, deployed within individual homes as part of a smart electricity grid, to converge to profitable and efficient behaviours. Specifically, we propose the use of software agents, residing on the users' smart meters, to automate and optimise the charging cycle of micro-storage devices in the home to minimise its costs, and we present a study of both the theoretical underpinnings and the implications of a practical solution, of using software agents for such micro-storage management. First, by formalising the strategic choice each agent makes in deciding when to charge its battery, we develop a game-theoretic framework within which we can analyse the competitive equilibria of an electricity grid populated by such agents and hence predict the best consumption profile for that population given their battery properties and individual load profiles. Our framework also allows us to compute theoretical bounds on the amount of storage that will be adopted by the population. Second, to analyse the practical implications of micro-storage deployments in the grid, we present a novel algorithm that each agent can use to optimise its battery storage profile in order to minimise its owner's costs. This algorithm uses a learning strategy that allows it to adapt as the price of electricity changes in real-time, and we show that the adoption of these strategies results in the system converging to the theoretical equilibria. Finally, we empirically evaluate the adoption of our micro-storage management technique within a complex setting, based on the UK electricity market, where agents may have widely varying load profiles, battery types, and learning rates. In this case, our approach yields savings of up to 14% in energy cost for an average consumer using a storage device with a capacity of less than 4.5 kWh and up to a 7% reduction in carbon emissions resulting from electricity generation (with only domestic consumers adopting micro-storage and, commercial and industrial consumers not changing their demand). Moreover, corroborating our theoretical bound, an equilibrium is shown to exist where no more than 48% of households would wish to own storage devices and where social welfare would also be improved (yielding overall annual savings of nearly £1.5B).

The capacity to adapt can greatly influence the success of systems that need to compensate for damaged parts, learn how to achieve robust performance in new environments, or exploit novel opportunities that originate from new technological interfaces or emerging markets. Many of the conditions in which technology is required to adapt cannot be anticipated during its design stage, creating a significant challenge for the designer. Inspired by the study of a range of biological systems, we propose that degeneracy - the realization of multiple, functionally versatile components with contextually overlapping functional redundancy - will support adaptation in technologies because it effects pervasive flexibility, evolutionary innovation, and homeostatic robustness. We provide examples of degeneracy in a number of rudimentary living technologies from military socio-technical systems to swarm robotics and we present design principles - including protocols, loose regulatory coupling, and functional versatility - that allow degeneracy to arise in both biological and man-made systems.