United Kingdom

The demand for intelligent virtual advisors in our rapidly advancing world is rising and, consequently, the need for understanding the reasoning process to answer why a particular piece of advice is provided to the user is directly increasing. Personalized explanation is regarded as a reliable way to improve the user&#39;s understanding and trust in the virtual advisor. So far, cognitive explainable agents utilize reason explanation by referring to their own mental state (beliefs and goals) to explain their own behaviour. However, when the explainable agent plays the role of a virtual advisor and recommends a behaviour for the human to perform, it is best to refer to the user&#39;s mental state, rather than the agent’s mental state, to form a reason explanation. In this paper, we are developing an explainable virtual advisor (XVA) that communicates with the user to elicit the user&#39;s beliefs and goals and then tailors its advice and explains it according to the user&#39;s mental state. We tested the proposed XVA with university students where the XVA provides tips to reduce the students&#39; study stress. We measured the impact of receiving three different patterns of tailored explanations (belief-based, goal-based, and belief&amp;goal-based explanation) in terms of the students&#39; intentions to change their behaviours. The results showed that the intention to change is not only related to the explanation pattern but also to the user context, the relationship built with the agent, the type of behaviour recommended and the user’s current intention to do the behaviour.

AAMAS 2021

Reason Explanation for Encouraging Behaviour Change Intention

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 

The demand for intelligent virtual advisors in our rapidly advancing world is rising and, consequently, the need for understanding the reasoning process to answer why a particular piece of advice is provided to the user is directly increasing. Personalized explanation is regarded as a reliable way to improve the user's understanding and trust in the virtual advisor. So far, cognitive explainable agents utilize reason explanation by referring to their own mental state (beliefs and goals) to explain their own behaviour. However, when the explainable agent plays the role of a virtual advisor and recommends a behaviour for the human to perform, it is best to refer to the user's mental state, rather than the agent’s mental state, to form a reason explanation. In this paper, we are developing an explainable virtual advisor (XVA) that communicates with the user to elicit the user's beliefs and goals and then tailors its advice and explains it according to the user's mental state. We tested the proposed XVA with university students where the XVA provides tips to reduce the students' study stress. We measured the impact of receiving three different patterns of tailored explanations (belief-based, goal-based, and belief&goal-based explanation) in terms of the students' intentions to change their behaviours. The results showed that the intention to change is not only related to the explanation pattern but also to the user context, the relationship built with the agent, the type of behaviour recommended and the user’s current intention to do the behaviour.

technical paper

Centralized Training for Decentralized Execution, where agents are trained offline using centralized information but execute in a decentralized manner online, has gained popularity in the multi-agent reinforcement learning community. In particular, actor-critic methods with a centralized critic and decentralized actors are a common instance of this idea. However, the implications of using a centralized critic in this context are not fully discussed and understood even though it is the standard choice of many algorithms. We therefore formally analyze centralized and decentralized critic approaches, providing a deeper understanding of the implications of critic choice. Because our theory makes unrealistic assumptions, we also empirically compare the centralized and decentralized critic methods over a wide set of environments to validate our theories and to provide practical advice. We show that there exist misconceptions regarding centralized critics in the current literature and show that the centralized critic design is not strictly beneficial, but rather both centralized and decentralized critics have different pros and cons that should be taken into account by algorithm designers.

Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learning

Value-based methods of multi-agent reinforcement learning (MARL), especially the value decomposition methods, have been demonstrated on a range of challenging cooperative tasks. However, current methods pay little attention to the interaction between agents, which is essential to teamwork in games or real life. This limits the efficiency of value-based MARL algorithms in the two aspects: collaborative exploration and value function estimation.  In this paper, we propose a novel cooperative MARL algorithm named as interactive actor-critic (IAC), which models the interaction of agents from the perspectives of policy and value function.  On the policy side, a multi-agent joint stochastic policy is introduced by adopting a collaborative exploration module, which is trained by maximizing the entropy-regularized expected return. On the value side, we use the shared attention mechanism to estimate the value function of each agent, which takes the impact of the teammates into consideration. At the implementation level, we extend the value decomposition methods to continuous control tasks and evaluate IAC on benchmark tasks including classic control and multi-agent particle environments. Experimental results indicate that our method outperforms the state-of-the-art approaches and achieves better performance in terms of cooperation.

Modeling the Interaction between Agents in Cooperative Multi-Agent Reinforcement Learning

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.

Reason Explanation for Encouraging Behaviour Change Intention

Downloads

Next from AAMAS 2021

Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learning

Similar lecture

Social Network Interventions to Prevent Reciprocity-driven Polarization

Reason Explanation for Encouraging Behaviour Change Intention

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAMAS 2021

Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learning

Similar lecture

Social Network Interventions to Prevent Reciprocity-driven Polarization

Downloads