Language games for autonomous robots

Integration and grounding are key AI challenges for human-robot dialogue. The author and his team are tackling these issues using language games and have experimented with them on progressively more complex platforms. A language game is a sequence of verbal interactions between two agents situated in a specific environment. Language games both integrate the various activities required for dialogue and ground unknown words or phrases in a specific context, which helps constrain possible meanings.     

游戏引擎启示录

垂涎"武装突袭2"这款游戏许久,它终于在今年发布了。在被其强悍的真实感震惊的同时,也听说这款游戏已经成为了美国军方的陆军部队专用训练软件。如今的游戏,无论从特效还是运行效率等各方面都发生了质的变化:"狂野西部:生死同盟"的第一作,由于其细腻的画质,成为ATI用来宣传DX10的御用游戏;Lithtech的代表作F.E.A.R首次引入了软阴影;画面和物理效果上都首屈一指的WOW,也吸引了诸多玩家为之驻足。而在这些背后,起到至关重要作用的正是游戏引擎的发展,游戏引擎都如同汽车的发动机,成为了一个游戏的核心和动力。     

To Commit or Not to Commit: Modeling Agent Conversations for Action

Conversations are sequences of messages exchanged among interacting agents. For conversations to be meaningful, agents ought to follow commonly known specifications limiting the types of messages that can be exchanged at any point in the conversation. These specifications are usually implemented using conversation policies (which are rules of inference) or conversation protocols (which are predefined conversation templates). In this article we present a semantic model for specifying conversations using conversation policies. This model is based on the principles that the negotiation and uptake of shared social commitments entail the adoption of obligations to action, which indicate the actions that agents have agreed to perform. In the same way, obligations are retracted based on the negotiation to discharge their corresponding shared social commitments. Based on these principles, conversations are specified as interaction specifications that model the ideal sequencing of agent participations negotiating the execution of actions in a joint activity. These specifications not only specify the adoption and discharge of shared commitments and obligations during an activity, but also indicate the commitments and obligations that are required (as preconditions) or that outlive a joint activity (as postconditions). We model the Contract Net Protocol as an example of the specification of conversations in a joint activity.     

Negotiating Dialogue Games

Recently in the field of agent communication, many authors have adopted the view of interaction as a joint activity regulated by means of dialogue games. It is argued in particular that this approach should increase the flexibility of dialogues by allowing a variety of game compositions. In this research note, we present a framework suited to this feature. A preliminary attempt to capture the negotiation phase (which allows agents to agree upon the dialogue game currently regulating their conversation) is discussed.     

Dialogue patterns—A visual language for dynamic dialogue

A dynamic dialogue is a conversation in which each participant alternately selects remarks based on a changing world state and in which each remark can change the world state. Dynamic dialogues happen frequently as conversations between a player character (PC) and a non-player character (NPC) in a computer game. When it is the PC's turn to speak, the current game state is used to filter the static set of remarks available to the PC to a contextually appropriate subset that is made available to the player. Selecting a PC remark then leads to a candidate set of NPC remarks as appropriate responses to the PC. The world state is used to filter this set of remarks to a single remark, which is used by the NPC as the reply. To construct a dynamic dialogue, an author must not only create the remarks, but also write the code that determines which remarks are available to both participants at any point in the dialogue. We present “generative dialogue patterns” as a new visual language for designing dynamic dialogues and generating the program code that is necessary to select the appropriate remarks during the dialogue. We use a case study from the computer games domain to evaluate the effectiveness of generative dialogue patterns.     

Model checking probabilistic social commitments for intelligent agent communication

Interaction among autonomous agents in Multi-Agent Systems (MASs) is a key aspect for agents to coordinate with one another. Social approaches, as opposed to the mental approaches, have recently received a considerable attention in the area of agent communication. They exploit observable social commitments to develop a verifiable formal semantics through which communication protocols can be specified. Developing and implementing algorithmic model checking for social commitments have been recently addressed. However, model checking social commitments in the presence of uncertainty is yet to be investigated.In this paper, we propose a model checking technique for verifying social commitments in uncertain settings. Social commitments are specified in a modal logical language called Probabilistic Computation Tree Logic of Commitments (PCTLC). The modal logic PCTLC extends PCTL, the probabilistic extension of CTL, with modalities for commitments and their fulfillments. The proposed verification method is a reduction-based model checking technique to the model checking of PCTL. The technique is based upon a set of reduction rules that translate PCTLC formulae to PCTL formulae to take benefit of existing model checkers such as PRISM. Proofs that confirm the soundness of the reduction technique are presented. We also present rules that transform our new version of interpreted systems into models of Markov Decision Processes (MDPs) to be suitable for the PRISM tool. We implemented our approach on top of the PRISM model checker and verified some given properties for the Oblivious Transfer Protocol from the cryptography domain. Our simulation demonstrates the effectiveness of our approach in verifying and model checking social commitments in the presence of uncertainty. We believe that the proposed formal verification technique will advance the literature of social commitments in such a way that not only representing social commitments in uncertain settings is doable, but also verifying them in such settings becomes achievable.     

A case based reasoning model for multilingual language generation in dialogues

The process of Natural Language Generation for a Conversational Agent translates some semantic language to its surface form expressed in natural language. In this paper, we are going to show a Case Based Reasoning technique which is easily extensible and adaptable to multiple domains and languages, that generates coherent phrases and produces a natural outcome in the context of a Conversational Agent that maintains a dialogue with the user.     

Coordinating Agents in Organizations Using Social Commitments

One of the main challenges faced by the multi-agent community is to ensure the coordination of autonomous agents in open heterogeneous multi-agent systems. In order to coordinate their behaviour, the agents should be able to interact with each other. Social commitments have been used in recent years as an answer to the challenges of enabling heterogeneous agents to communicate and interact successfully. However, coordinating agents only by means of interaction models is difficult in open multi-agent systems, where possibly malevolent agents can enter at any time and violate the interaction rules. Agent organizations, institutions and normative systems have been used to control the way agents interact and behave. In this paper we try to bring together the two models of coordinating agents: commitment-based interaction and organizations. To this aim we describe how one can use social commitments to represent the expected behaviour of an agent playing a role in an organization. We thus make a first step towards a unified model of coordination in multi-agent systems: a definition of the expected behaviour of an agent using social commitments in both organizational and non-organizational contexts.     

Measuring and analyzing agents’ uncertainty in argumentation-based negotiation dialogue games

Nowadays, multiagent systems have become a widely used technology in everyday life, and many authors have adopted the view of communication or interaction between agents as a joint activity regulated by means of dialogue games. Dialogue games are a set of communication rules that agents can combine in their complex interactions. In these games, uncertainty is an important problem that each agent faces when making decisions, especially in the absence of enough information. This paper focuses on the uncertainty in a particular type of dialogue games, namely argumentation-based negotiation. There exist several proposals on this type of dialogue games in the literature, and most of them are concerned with proposing protocols to show how agents can communicate with each other, and how arguments and offers can be generated, evaluated and exchanged. Nevertheless, none of them is directly targeting the agents’ uncertainty about the exchanged arguments and how this uncertainty could be measured at each dialogue step to assist those agents make better decisions. The aim of this paper is to tackle this problem by defining a new set of uncertainty measures in negotiation dialogue games from an external agent’s point of view. In particular, we introduce two types of uncertainty: Type I and Type II. Type I is about the uncertainty index of playing the right move. For this, we use Shannon entropy to measure: (i) the uncertainty index of the agent that he is selecting the right move at each dialogue step; and (ii) the uncertainty index of participating agents in the negotiation about the whole dialogue. This is done in two different ways; the first is by taking the average of the uncertainty index of all moves, and the second is by determining all possible dialogues and applying the general formula of Shannon entropy. Type II is about the uncertainty degree of the agent that the move will be accepted by the addressee. In this context, we introduce a new classification for the arguments based on their certainty to be accepted by the addressee.     

Dialogue games that agents play within a society

Human societies have long used the capability of argumentation and dialogue to overcome and resolve conflicts that may arise within their communities. Today, there is an increasing level of interest in the application of such dialogue games within artificial agent societies. In particular, within the field of multi-agent systems, this theory of argumentation and dialogue games has become instrumental in designing rich interaction protocols and in providing agents with a means to manage and resolve conflicts. However, to date, much of the existing literature focuses on formulating theoretically sound and complete models for multi-agent systems. Nonetheless, in so doing, it has tended to overlook the computational implications of applying such models in agent societies, especially ones with complex social structures. Furthermore, the systemic impact of using argumentation in multi-agent societies and its interplay with other forms of social influences (such as those that emanate from the roles and relationships of a society) within such contexts has also received comparatively little attention. To this end, this paper presents a significant step towards bridging these gaps for one of the most important dialogue game types; namely argumentation-based negotiation (ABN). The contributions are three fold. First, we present a both theoretically grounded and computationally tractable ABN framework that allows agents to argue, negotiate, and resolve conflicts relating to their social influences within a multi-agent society. In particular, the model encapsulates four fundamental elements: (i) a scheme that captures the stereotypical pattern of reasoning about rights and obligations in an agent society, (ii) a mechanism to use this scheme to systematically identify social arguments to use in such contexts, (iii) a language and a protocol to govern the agent interactions, and (iv) a set of decision functions to enable agents to participate in such dialogues. Second, we use this framework to devise a series of concrete algorithms that give agents a set of ABN strategies to argue and resolve conflicts in a multi-agent task allocation scenario. In so doing, we exemplify the versatility of our framework and its ability to facilitate complex argumentation dialogues within artificial agent societies. Finally, we carry out a series of experiments to identify how and when argumentation can be useful for agent societies. In particular, our results show: a clear inverse correlation between the benefit of arguing and the resources available within the context; that when agents operate with imperfect knowledge, an arguing approach allows them to perform more effectively than a non-arguing one; that arguing earlier in an ABN interaction presents a more efficient method than arguing later in the interaction; and that allowing agents to negotiate their social influences presents both an effective and an efficient method that enhances their performance within a society.     

Multi-Agent Modeling Toolkit – MAMT

Multi-agent system consists of two or more agents which cooperate/coordinate with each other in order to solve a complex problem which would be difficult or inappropriate if solved by single agent. Multi-agents are modeled using Agent Unified Modeling Language (AUML) as Unified Modeling Language (UML) notations do not fully express agent properties/behaviors. In this paper, we have proposed Multi-Agent Modeling Toolkit (MAMT) to help a designer in building rapid multi-agent based applications. The purpose of this toolkit is to create agent development environment where the developer can have various facilities like reusability of existing/developed agents, customize built-in agents, etc. MAMT provides the designer with built-in agents which are developed using Java Agent Development (JADE) framework, with the help of these designers can rapidly build multi-agent based applications. Creation and customization of built-in agents is based on the prototype inclusion design pattern and the designer can add or modify methods/behaviors according to their requirement(s); however the changes should be based on FIPA (Foundation of Intelligent Physical Agents) standards and compatible with JADE. MAMT has been evaluated on large number of sample applications; results were very promising and encourage the use of toolkit.     

Agent communication and artificial institutions

In this paper we propose an application-independent model for the definition of artificial institutions that can be used to define open multi-agent systems. Such a model of institutional reality makes us able also to define an objective and external semantics of a commitment-based Agent Communication Language (ACL). In particular we propose to regard an ACL as a set of conventions to act on a fragment of institutional reality, defined in the context of an artificial institution. Another contribution of the work presented in this paper is an operational definition of norms, a crucial component of artificial institutions. In fact in open systems interacting agents might not conform to the specifications. We regard norms as event-driven rules that when are fired by events happening in the system create or cancel a set of commitments. An interesting aspect of our proposal is that both the definition of the ACL and the definition of norms are based on the same notion of commitment. Therefore an agent capable of reasoning on commitments can reason on the semantics of communicative acts and on the system of norms.     

A Geometric Semantics for Dialogue Game Protocols for Autonomous Agent Interactions

Formal dialogue games studied by philosophers since the time of Aristotle have recently found application in Artificial Intelligence as the basis for protocols for interactions between autonomous software agents. For instance, game protocols have been proposed for agent dialogues involving team formation, persuasion, negotiation and deliberation. There is yet, however, no formal, mathematical theory of dialogue game protocols with which to compare two protocols or to study their formal properties. In this paper,¹ we present preliminary work towards such a theory, in which we develop a geometric semantics for these protocols and, with it, define a notion of equivalence between two protocols. We then demonstrate an algebraic property of protocol equivalence, and use this to show the non-equivalence of two similar generic protocols. We also explore the relationship between finite and infinite dialogues, motivated by the Ehrenfeucht-Fraïssé games of model theory. Our results have implications for the design and evaluation of agent dialogue-game protocols.     

Extending Answer Sets for Logic Programming Agents

We present systems of logic programming agents (LPAS) to model the interactions between decision-makers while evolving to a conclusion. Such a system consists of a number of agents connected by means of unidirectional communication channels. Agents communicate with each other by passing answer sets obtained by updating the information received from connected agents with their own private information. We introduce a credulous answer set semantics for logic programming agents. As an application, we show how extensive games with perfect information can be conveniently represented as logic programming agent systems, where each agent embodies the reasoning of a game player, such that the equilibria of the game correspond with the semantics agreed upon by the agents in the LPAS.     

一种基于社会承诺的Agent组织模型OMSC

多Agent领域所面临的一个重大的挑战是解决开放异质的多Agent系统中自治Agent间的协调问题。多Agent为了协调它们之间的活动,需要进行交互。社会承诺作为一种通信和交互机制,为自治的多Agent提供了一种协调的途径。然而,仅靠交互难以实现多Agent间的协调。Agent组织作为一种协调模型可以有效地控制多Agent间的交互与合作。论文将社会承诺和Agent组织两种协调机制相结合,提出一种基于社会承诺的Agent组织模型OMSC,分析了Agent如何用社会承诺进行推理以及基于社会承诺的多Agent系统并给出了一个实例,为多Agent间的协调提供了一种新的方法。     

Inferring social nature of conversations from words: Experiments on a corpus of everyday telephone conversations

Language is being increasingly harnessed to not only create natural human–machine interfaces but also to infer social behaviors and interactions. In the same vein, we investigate a novel spoken language task, of inferring social relationships in two-party conversations: whether the two parties are related as family, strangers or are involved in business transactions. For our study, we created a corpus of all incoming and outgoing calls from a few homes over the span of a year. On this unique naturalistic corpus of everyday telephone conversations, which is unlike Switchboard or any other public domain corpora, we demonstrate that standard natural language processing techniques can achieve accuracies of about 88%, 82%, 74% and 80% in differentiating business from personal calls, family from non-family calls, familiar from unfamiliar calls and family from other personal calls respectively. Through a series of experiments with our classifiers, we characterize the properties of telephone conversations and find: (a) that 30 words of openings (beginnings) are sufficient to predict business from personal calls, which could potentially be exploited in designing context sensitive interfaces in smart phones; (b) our corpus-based analysis does not support Schegloff and Sack's manual analysis of exemplars in which they conclude that pre-closings differ significantly between business and personal calls – closing fared no better than a random segment; and (c) the distribution of different types of calls are stable over durations as short as 1–2 months. In summary, our results show that social relationships can be inferred automatically in two-party conversations with sufficient accuracy to support practical applications.     

Endogenous Movement and Equilibrium Selection in Spatial Coordination Games

We study the effects of agent movement on equilibrium selection in network based spatial coordination games with Pareto dominant and risk dominant Nash equilibria. Our primary interest is in understanding how endogenous partner selection on networks influences equilibrium selection in games with multiple equilibria. We use agent based models and best response behaviors of agents to study our questions of interest. In general, we find that allowing agents to move and choose new game play partners greatly increases the probability of attaining the Pareto dominant Nash equilibrium in coordination games. We also find that agent diversity increases the ability of agents to attain larger payoffs on average.     

Software agents for knowledge management: coordination in multi-agent supply chains and auctions

A fundamental question that must be addressed in software agents for knowledge management is coordination in multi-agent systems. The coordination problem is ubiquitous in knowledge management, such as in manufacturing, supply chains, negotiation, and agent-mediated auctions. This paper summarizes several multi-agent systems for knowledge management that have been developed recently by the author and his collaborators to highlight new research directions for multi-agent knowledge management systems. In particular, the paper focuses on three areas of research:

• •Coordination mechanisms in agent-based supply chains. How do we design mechanisms for coordination, information and knowledge sharing in supply chains with self-interested agents? What would be a good coordination mechanism when we have a non-linear structure of the supply chain, such as a pyramid structure? What are the desirable properties for the optimal structure of efficient supply chains in terms of information and knowledge sharing? Will DNA computing be a viable tool for the analysis of agent-based supply chains?
• •Coordination mechanisms in agent-mediated auctions. How do we induce cooperation and coordination among various self-interested agents in agent-mediated auctions? What are the fundamental principles to promote agent cooperation behavior? How do we train agents to learn to cooperate rather than program agents to cooperate? What are the principles of trust building in agent systems?
• •Multi-agent enterprise knowledge management, performance impact and human aspects. Will people use agent-based systems? If so, how do we coordinate agent-based systems with human beings? What would be the impact of agent systems in knowledge management in an information economy?