United Kingdom

Relational agents who personalise their message to individual users need to learn about the user first. In the context of an agent who personalises the inclusion of 10 relational cues in its dialogue, we explore training the agent based on first time user’s responses to a single example of each cue prior to the session with the virtual advisor. We designed a between subjects study with three groups: Empathic (all relational cues); Neutral (no relational cues) and Adaptive (only helpful cues included). We found that in the Adaptive group, students received what they found helpful more often than in the other two groups. Analysis of the discrepancy between what user’s found helpful and what they received was least in the Adaptive group and greatest in the Neutral group.

AAMAS 2021

Personalising the Dialogue of Relational Agents for First-Time Users

AAMAS is the largest and most influential conference in the area of agents and multiagent systems, bringing together researchers and practitioners in all areas of agent technology and providing and internationally renowned high-profile forum for publishing and finding out about the latest developments in the field. AAMAS is the flagship conference of the non-profit International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).  

![](https://assets.underline.io/uploads/markdown_image/1/image/ce4604bd54468a006164d16e080204fb.jpg)

Please click on the button below to register for this event.

If you are registered and see this page please check the account email you are logged in with. It must be the same as for the registration.

If you still have trouble accessing the contact please contact support at aamas2021@underline.io 

poster

Conversational agents have been widely adopted in dialogue systems for various business purposes. Many existing conversational agents are rule-based and require significant human intervention to adapt the knowledge and conversational flow. In this paper, we propose a graph-based adaptive conversational agent model which is capable of learning knowledge from human beings and adapting the knowledge-base according to human-agent interactions. Studies to evaluate the proposed model are conducted and presented, which compare the responses from the proposed adaptive agent model and a conventional agent.

Graph-based Self-Adaptive Conversational Agent

Automatic gesture generation from speech generally relies on implicit modelling of the nondeterministic speech-gesture relationship and can result in averaged motion lacking defined form. Here, we propose a database-driven approach of selecting gestures based on specific motion characteristics that have been shown to be associated with the speech audio. We extend previous work that identified expressive parameters of gesture motion that can both be predicted from speech and are perceptually important for a good speech-gesture match, such as gesture velocity and finger extension. A perceptual study was performed to evaluate the appropriateness of the gestures selected with our method. We compare our method with two baseline selection methods. The first respects timing, the desired onset and duration of a gesture, but does not match gesture form in other ways. The second baseline additionally disregards the original gesture timing for selecting gestures. The gesture sequences from our method were rated as a significantly better match to the speech than gestures selected by either baseline method.

It's A Match! Gesture Generation Using Expressive Parameter Matching

SARSA-RS is a reward shaping method that updates the shaping through learning. However, the bottleneck of this method is the aggregation of states since designers need to design mappings from all states to abstract states. We propose a dynamic trajectory aggregation that uses subgoal series. The designer's effort becomes minimal because only human input is the subgoal series. This makes application to environments with high-dimensional observations possible. We compared our method by using participants' subgoal series with a baseline reinforcement learning algorithm and other subgoal-based methods in a navigation task. As a result, our reward shaping outperformed all other methods in learning efficiency.

Online Learning of Shaping Reward with Subgoal Knowledge

Competitive Multi-Agent Systems (MAS) are inherently hard to control due to agent autonomy and strategic behavior, which is particularly problematic when there are system-level objectives to be achieved or specific environmental states to be avoided.

Toward a Self-Learning Governance Loop for Competitive Multi-Attribute MAS

Large scale multiagent systems must rely on distributed decision making, as centralized coordination is either impractical or impossible. Recent works approach this problem under a game theoretic lens, whereby utility functions are assigned to each of the agents with the hope that their local optimization approximates the centralized optimal solution. Yet, formal guarantees on the resulting performance cannot be obtained for broad classes of problems without compromising on their accuracy. In this work, we address this concern relative to the well-studied problem of resource allocation with nondecreasing concave welfare functions. We show that optimally designed local utilities achieve an approximation ratio (price of anarchy) of 1-c/e, where c is the function's curvature and e is Euler's constant. The upshot of our contributions is the design of approximation algorithms that are distributed and efficient, and whose performance matches that of the best existing polynomial-time (and centralized) schemes.

Tractable Mechanisms for Computing Near-Optimal Utility Functions

We introduce the idea of a finite sequence of coalition formation games over a set of agents, and we call it Sequential Characteristic-Function Game (SCFG). We define the solution of such a game as a corresponding sequence of coalition structures that must be related by a given feasibility relation, so no coalition structure can be evaluated in isolation. A sequence satisfying this condition is called Feasible Coalition-Structure Sequence (FCSS). Such games can be a useful abstraction for modelling various scenarios, in particular those for real-world disaster management that we consider in this paper. We give an algorithm for computing an FCSS and evaluate it experimentally. Our results show that an SCFG can represent various classical variations of characteristic-function games, and our algorithm solves instances with a reasonable number of agents.

Feasible Coalition Sequences

A set of players delegate playing a game to a set of representatives, one for each player. We imagine that each player trusts their respective representative's strategic abilities. Thus, we might imagine that per default, the original players would simply instruct the representatives to play the original game as best as they can. In this paper, we ask: are there safe Pareto improvements on this default way of giving instructions? That is, we imagine that the original players can coordinate to tell their representatives to only consider some subset of the available strategies and to assign utilities to outcomes differently than the original players. Then can the original players do this in such a way that the payoff is guaranteed to be weakly higher than under the default instructions for all the original players? In particular, can they Pareto-improve without probabilistic assumptions about how the representatives play games? In this paper, we give some examples of safe Pareto improvements. We prove that the notion of safe Pareto improvements is closely related to a notion of outcome correspondence between games. We also show that under some specific assumptions about how the representatives play games, finding safe Pareto improvements is NP-complete.

Safe Pareto Improvements for Delegated Game Playing

The problem of finding pure strategy Nash equilibria in multiagent concurrent games with finite-horizon temporal goals has received some recent attention. Earlier work solved this problem through the use of Rabin automata. In this work, we take advantage of the finite-horizon nature of the agents' goals and show that checking for and finding pure strategy Nash equilibria can be done using a combination of safety games and lasso testing in B&#252;chi automata. To separate strategic reasoning from temporal reasoning, we model agents' goals by deterministic finite-word automata (DFAs), since finite-horizon logics such as LTL<sub>f</sub> and LDL<sub>f</sub> are reasoned about through conversion to equivalent DFAs. This allow us characterize the complexity of the problem as PSPACE complete.

Nash Equilibria in Finite-Horizon Multiagent Concurrent Games

In this paper, we propose and study the cascade submodular maximization problem under the adaptive setting. The input of our problem is a set of items, each item is in a particular state (i.e., the marginal contribution of an item) which is drawn from a known probability distribution. However, we can not know its actual state before selecting it. As compared with existing studies on stochastic submodular maximization, one unique setting of our problem is that each item is associated with a continuation probability which represents the probability that one is allowed to continue to select the next item after selecting the current one. Intuitively, this term captures the externality of selecting one item to all its subsequent items in terms of the opportunity of being selected.  Therefore, the actual set of items that can be selected by a policy depends on the specific ordering it adopts to select items, this makes our problem fundamentally different from classical submodular set optimization problems. Our objective is to identify the best sequence of selecting items so as to maximize the expected utility of the selected items. We propose a class of stochastic utility functions, adaptive cascade submodular functions, and show that the objective functions in many practical application domains satisfy adaptive cascade submodularity. Then we develop a $0.12$ approximation algorithm to the adaptive cascade submodular maximization problem.

Adaptive Cascade Submodular Maximization

Embodied conversational agents (ECAs) benefit from non-verbal behavior for natural and efficient interaction with users. Gesticulation -- hand and arm movements accompanying speech -- is an essential part of non-verbal behavior. Gesture generation models have been developed for several decades: starting with rule-based and ending with mainly data-driven methods. To date, recent end-to-end gesture generation methods have not been evaluated in a real-time interaction with users. We present a proof-of-concept framework, which is intended to facilitate evaluation of modern gesture generation models in interaction.

Personalising the Dialogue of Relational Agents for First-Time Users

Next from AAMAS 2021

Graph-based Self-Adaptive Conversational Agent

Similar lecture

Group Fairness for Knapsack Problems

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES