United Kingdom

This paper presents objective metrics for how explainable artificial intelligence (XAI) can be quantified. Through an overview of current trends, we show that many explanations are generated post-hoc and independent of the agent&#39;s logical process, which in turn creates explanations with limited meaning as they lack transparency and fidelity. While user studies are a known basis for evaluating XAI, studies that do not consider objective metrics for evaluating XAI may have limited meaning and may suffer from confirmation bias, particularly if they use low fidelity explanations unnecessarily. To avoid this issue, this paper suggests a paradigm shift in evaluating XAI that focuses on metrics that quantify the explanation itself and its appropriateness given the XAI goal. We suggest four such metrics based on performance differences, D, between the explanation&#39;s logic and the agent&#39;s actual performance, the number of rules, R, outputted by the explanation, the number of features, F, used to generate that explanation, and the stability, S, of the explanation. We believe that user studies that focus on these metrics in their evaluations are inherently more valid and should be integrated in future XAI research.

AAMAS 2021

Better Metrics for Evaluating Explainable Artificial Intelligence (Blue Sky Ideas Track)

We are pleased to announce the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), which will be held in Vancouver, British Columbia at the Vancouver Convention Centre – West Building from 20-27 February, 2024.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-24 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

We expect for AAAI-24 to be an in-person conference – one author of all accepted papers will be expected to present work in person unless there are exceptional circumstances that prevent this.<br><br><br><br>

In order to access the AAAI-24 event page you need to register [here](https://aaai.org/aaai-conference/registration/)

AAAI 2024

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. 

This paper presents objective metrics for how explainable artificial intelligence (XAI) can be quantified. Through an overview of current trends, we show that many explanations are generated post-hoc and independent of the agent's logical process, which in turn creates explanations with limited meaning as they lack transparency and fidelity. While user studies are a known basis for evaluating XAI, studies that do not consider objective metrics for evaluating XAI may have limited meaning and may suffer from confirmation bias, particularly if they use low fidelity explanations unnecessarily. To avoid this issue, this paper suggests a paradigm shift in evaluating XAI that focuses on metrics that quantify the explanation itself and its appropriateness given the XAI goal. We suggest four such metrics based on performance differences, D, between the explanation's logic and the agent's actual performance, the number of rules, R, outputted by the explanation, the number of features, F, used to generate that explanation, and the stability, S, of the explanation. We believe that user studies that focus on these metrics in their evaluations are inherently more valid and should be integrated in future XAI research.

technical paper

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.

Reason Explanation for Encouraging Behaviour Change Intention

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.

Downloads

Next from AAMAS 2021

Reason Explanation for Encouraging Behaviour Change Intention

Similar lecture

Evaluating the Effectiveness of Explainable Artificial Intelligence Approaches (Student Abstract)

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.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

Reason Explanation for Encouraging Behaviour Change Intention

Similar lecture

Evaluating the Effectiveness of Explainable Artificial Intelligence Approaches (Student Abstract)

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads