[TMP-005] A model and architecture for multi-context, value-aware agents

Contact person: Rui Prada (rui.prada@tecnico.ulisboa.pt)

Internal Partners:

1. IST, Rui Prada, rui.prada@tecnico.ulisboa.pt @tudelft.nl 
2. Umeå University (UmU), Juan Carlos Nieves, jcnieves@cs.umu.s   

External Partners:

1. UPC
2. Bath  

This project aims at developing an explicit representation and interpretation of stakeholders’ socio-ethical values, conventions, and norms, and to incorporate them in AIS component reasoning and decision-making processes. By doing so, we can enable ethics-by-design approaches in which the agents take into consideration the wider socio-ethical values that they are meant to fulfil as part of the socio-ethical systems that they belong to.

There is extensive literature on the formalisation of value systems, norms, and conventions, but most works cover only one level of abstraction at one end of the spectrum – either abstract and universal or concrete and specific to a particular scenario – and in a single interaction context. However, the real social world is much more complex with multiple overlapping contexts that comprise extended sequences of events within contexts, while events can individually and severally have effects across contexts. There are multiple – not fully compatible – value theories, such as Self-Determination Theory or the Schwartz Value System. These are also abstract in nature and not directly applicable to an agent’s behaviour. A key factor in understanding how values affect actions is that preferences over values are context-dependent, so certain values are more important than others according to the circumstances. This becomes more complicated when we consider that an agent can be in more than one context at the same time and thus have to handle different, possibly conflicting, preference orderings. Lastly, there is the mutual interaction of values with context to address: the context affects the value preferences, but also value preferences affect the context. Consequently, to formalise value preferences for agents, we need to identify and define a suitable approximation of a context for the purposes of this microproject.

In this microproject, we develop:

1. A novel agent architecture that allows agents to be aware of the values/norms/conventions for each of the social contexts related to their interactions by creating separate explicit representations for each context, and then utilising these context representations in reasoning and decision making to align the resulting behaviour to the social values of the contexts in which the agent is situated.
2. A methodology to develop a multi-level, multi-contextual model to formalise a connection from abstract, universal social values to concrete behaviour of agents in a particular social context. More concretely, we aim to create a computational representation of nested, overlapping (eventually contradictory) social contexts, where the set of values and the preference function over them (and their respective norms and conventions) of a given context are properly derived from abstract values in higher-level, more general (super) contexts, up to universal, abstract values.

Results Summary

An exploratory exercise of values and preferences was carried out on a water consumption scenario.

An agent-based model (ABM) was developed and run, with values and value preferences as part of agents’ deliberation as well as contexts expressed as value preferences. Contexts affected agents in such a way that it may result in them temporarily changing their value preferences according to an effort function (we assumed such effort would be proportional to how much importance each agent gave to their values).

The projects’ outcomes show that:

• Adding value preferences and contexts delivers more realistic results in a water-consumption multi-agent simulation.
• Given our grounding in the Schwartz’s circumflex model of values and a value preference, some value orders are more prone to shift than others, that is, they are more flexible in terms of changing their preferences.

We wrote a workshop paper presenting the results of experimenting with such ABM.

Tangible Outcomes

1. [workshop] Oliva-Felipe, L., Lobo, I., McKinlay, J., Dignum, F., De Vos, M., Cortés, U., Cortés, A. (2024). Context Matters: Contextual Value-Based Deliberation in Water Consumption Scenarios. In: XXX, Y., et al. Artificial Intelligence. ECAI 2024 International Workshops. ECAI 2024. Communications in Computer and Information Science, vol XXXX. Springer, Cham. https://doi.org/XXXX/YYYYY (accepted, to be printed)
2. A software implementing the above-mentioned model. The code of the ABM can be found in this repository: https://github.com/HPAI-BSC/value-based-water-consumption/