Human interaction relies on a wide range of signals, including non-verbal cues. In order to develop effective Explainable Planning (XAIP) agents it is important that we understand the range and utility of these communication channels. Our starting point is existing results from joint task interaction and their study in cognitive science. Our intention is that these lessons can inform the design of interaction agents -- including those using planning techniques -- whose behaviour is conditioned on the user's response, including affective measures of the user (i.e., explicitly incorporating the user's affective state within the planning model). We have identified several concepts at the intersection of plan-based agent behaviour and joint task interaction and have used these to design two agents: one reactive and the other partially predictive. We have designed an experiment in order to examine human behaviour and response as they interact with these agents. In this paper we present the designed study and the key questions that are being investigated. We also present the results from an empirical analysis where we examined the behaviour of the two agents for simulated users.
Rochester Institute of Technology（罗切斯特理工学院）；University of Waterloo（滑铁卢大学）
One-sided matching mechanisms are fundamental for assigning a set of indivisible objects to a set of self-interested agents when monetary transfers are not allowed. Two widely-studied randomized mechanisms in multiagent settings are the Random Serial Dictatorship (RSD) and the Probabilistic Serial Rule (PS). Both mechanisms require only that agents specify ordinal preferences and have a number of desirable economic and computational properties. However, the induced outcomes of the mechanisms are often incomparable and thus there are challenges when it comes to deciding which mechanism to adopt…
University College London（伦敦大学学院）；Oxford University（牛津大学）；Imperial College London（帝国理工学院）
Biological agents have meaningful interactions with their environment despite the absence of immediate reward signals. In such instances, the agent can learn preferred modes of behaviour that lead to predictable states -- necessary for survival. In this paper, we pursue the notion that this learnt behaviour can be a consequence of reward-free preference learning that ensures an appropriate trade-off between exploration and preference satisfaction. For this, we introduce a model-based Bayesian agent equipped with a preference learning mechanism (pepper) using conjugate priors. These conjugate p…
University of Waterloo（滑铁卢大学）；Monash University（莫纳什大学）
We study active preference learning as a framework for intuitively specifying the behaviour of autonomous robots. In active preference learning, a user chooses the preferred behaviour from a set of alternatives, from which the robot learns the user's preferences, modeled as a parameterized cost function. Previous approaches present users with alternatives that minimize the uncertainty over the parameters of the cost function. However, different parameters might lead to the same optimal behaviour; as a consequence the solution space is more structured than the parameter space. We exploit this b…
The Physics of Preference: Unravelling Imprecision of Human Preferences through Magnetisation Dynamics
Artificial Intelligence and Cyber Futures Institute（人工智能与网络未来研究所）；Charles Sturt University（查尔斯斯特大学）；The Alan Turing Institute（阿兰·图灵研究所）；The University of Sydney Business School（悉尼大学商学院）
University College London（伦敦大学学院）；Huawei Technologies（华为技术有限公司）；Oxford University（牛津大学）；Imperial College London（帝国理工学院）
How can artificial agents learn non-reinforced preferences to continuously adapt their behaviour to a changing environment? We decompose this question into two challenges: ($i$) encoding diverse memories and ($ii$) selectively attending to these for preference formation. Our proposed \emph{no}n-\emph{re}inforced preference learning mechanism using selective attention, \textsc{Nore}, addresses both by leveraging the agent's world model to collect a diverse set of experiences which are interleaved with imagined roll-outs to encode memories. These memories are selectively attended to, using atten…
An important feature of pervasive, intelligent assistance systems is the ability to dynamically adapt to the current needs of their users. Hence, it is critical for such systems to be able to recognize those goals and needs based on observations of the user's actions and state of the environment. In this work, we investigate the application of two state-of-the-art, planning-based plan recognition approaches in a real-world setting. So far, these approaches were only evaluated in artificial settings in combination with agents that act perfectly rational. We show that such approaches have diffic…
University of Tasmania（塔斯马尼亚大学）；MyState Bank（MyState银行）；Australian Artificial Intelligence Institute（澳大利亚人工智能研究所）；University of Technology Sydney（悉尼科技大学）
The current reward learning from human preferences could be used to resolve complex reinforcement learning (RL) tasks without access to a reward function by defining a single fixed preference between pairs of trajectory segments. However, the judgement of preferences between trajectories is not dynamic and still requires human input over thousands of iterations. In this study, we proposed a weak human preference supervision framework, for which we developed a human preference scaling model that naturally reflects the human perception of the degree of weak choices between trajectories and estab…
In this paper, we investigate output accuracy for a Discrete Event Simulation (DES) model and Agent Based Simulation (ABS) model. The purpose of this investigation is to find out which of these simulation techniques is the best one for modelling human reactive behaviour in the retail sector. In order to study the output accuracy in both models, we have carried out a validation experiment in which we compared the results from our simulation models to the performance of a real system. Our experiment was carried out using a large UK department store as a case study. We had to determine an efficie…
Recent reinforcement learning studies extensively explore the interplay between cooperative and competitive behaviour in mixed environments. Unlike cooperative environments where agents strive towards a common goal, mixed environments are notorious for the conflicts of selfish and social interests. As a consequence, purely rational agents often struggle to achieve and maintain cooperation. A prevalent approach to induce cooperative behaviour is to assign additional rewards based on other agents' well-being. However, this approach suffers from the issue of multi-agent credit assignment, which c…
Inferring Affective Consciousness in an Artificial Agent: A Case Study
University of Cape Town（开普敦大学）；University of the Witwatersrand（威特沃特斯兰德大学）；Laureate Institute for Brain Research（劳雷亚德脑研究所）；University of Tulsa（塔尔萨大学）；Delft University of Technology（代尔夫特理工大学）；National Institute for Theoretical & Computational Sciences（国家理论与计算科学研究所）；Institut National de la recherche scientifique（国家科学研究所）
Diffusion models have emerged as powerful generative models in the text-to-image domain. This paper studies their application as observation-to-action models for imitating human behaviour in sequential environments. Human behaviour is stochastic and multimodal, with structured correlations between action dimensions. Meanwhile, standard modelling choices in behaviour cloning are limited in their expressiveness and may introduce bias into the cloned policy. We begin by pointing out the limitations of these choices. We then propose that diffusion models are an excellent fit for imitating human be…
