Chloe

Beyond goal-rationality: Traditional action can reduce volatility in socially situated agents

Authors

Chloe M. Barnes, Anikó Ekárt and Peter R. Lewis

Journal Details

Future Generation Computer Systems (FGCS).


Abstract

Systems that pursue their own goals in shared environments can indirectly affect one another in unanticipated ways, such that the actions of other systems can interfere with goal-achievement. As humans have evolved to achieve goals despite interference from others in society, we thus endow socially situated agents with the capacity for social action as a means of mitigating interference in co-existing systems. We demonstrate that behavioural and evolutionary volatility caused by indirect interactions of goal-rational agents can be reduced by designing agents in a more socially-sensitive manner. We therefore challenge the assumption that designers of intelligent systems typically make, that goal-rationality is sufficient for achieving goals in shared environments.

Coevolutionary Learning of Neuromodulated Controllers for Multi-Stage and Gamified Tasks

Authors

Chloe M. Barnes, Anikó Ekárt, Kai Olav Ellefsen, Kyrre Glette, Peter R. Lewis and Jim Tørresen

Conference Details

2020 IEEE 1st International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS)

Washington DC, USA (Virtual).

13th-18th July 2020.


Abstract

Neural networks have been widely used in agent learning architectures; however, learning multiple context-dependent tasks simultaneously or sequentially is problematic when using them. Behavioural plasticity enables humans and animals alike to respond to changes in context and environmental stimuli, without degrading learnt knowledge; this can be achieved by regulating behaviour with neuromodulation – a biological process found in the brain. We demonstrate that modulating activity-propagating signals when evolving neural networks enables agents to learn context-dependent and multi-stage tasks more easily. Further, we show that this benefit is preserved when agents occupy an environment shared with other neuromodulated agents. Additionally we show that neuromodulation helps agents that have evolved alone to adapt to changes in environmental stimuli when they continue to evolve in a shared environment.

A Minimal River Crossing Task to Aid the Explainability of Evolutionary Agents

Authors

Abida Ghouri, Chloe M. Barnes and Peter R. Lewis

Conference Details

The 2020 Conference on Artificial Life (ALife).

Montreál, Canada (Virtual).

13th-18th July 2020.


Abstract

Evolving agents to learn how to solve complex, multi-stage tasks to achieve a goal is a challenging problem. Problems such as the River Crossing Task are used to explore how these agents evolve and what they learn, but it is still often difficult to explain why agents behave in the way they do. We present the Minimal River Crossing (RC-) Task testbed, designed to reduce the complexity of the original River Crossing Task while keeping its essential components, such that the fundamental learning challenges it presents can be understood in more detail. Specifically to illustrate this, we demonstrate that the RC- environment can be used to investigate the effect that a cost to movement has on agent evolution and learning, and more importantly that the findings obtained as a result can be generalised back to the original River Crossing Task.

Social Action in Socially Situated Agents

Authors

Chloe M. Barnes, Anikó Ekárt and Peter R. Lewis

Conference Details

2019 IEEE 13th International Conference on Self-Adaptive and Self-Organizing Systems (SASO).

Umeå, Sweden.

16th-20th June 2019.


Abstract

Two systems pursuing their own goals in a shared world can interact in ways that are not so explicit-such that the presence of another system alone can interfere with how one is able to achieve its own goals. Drawing inspiration from human psychology and the theory of social action, we propose the notion of employing social action in socially situated agents as a means of alleviating interference in interacting systems. Here we demonstrate that these specific issues of behavioural and evolutionary instability caused by the unintended consequences of interactions can be addressed with agents capable of a fusion of goal-rationality and traditional action, resulting in a stable society capable of achieving goals during the course of evolution.

Beyond Goal-Rationality: Traditional Action Can Promote Goal-Achievement in Socially Situated Agents

It was a pleasure to speak at the Workshop on Evolution of Human Behaviour, at ALife 2019; the extended abstract below explores the impact of social action on the stability of learning and evolution in multi-agent systems.


Authors

Chloe M. Barnes, Anikó Ekárt and Peter R. Lewis

Workshop Details

2019 Workshop on Evolution of Human Behaviour. ALife 2019.

Newcastle-upon-Tyne, United Kingdom.

29th July 2019.


Excerpt

In this talk, we will explore the impact of purely goal-rational action on systems that are socially-situated, demonstrating that this can lead to instability in co-evolutionary learning. We will then show that by complementing goal-rational action with traditional action, more stable dynamics can be observed. We operationalise traditional action in this context as acting in a similar way to the rest of the population.

CHARIOT – Towards a Continuous High-level Adaptive Runtime Integration Testbed

Authors

Chloe M. Barnes, Kirstie Bellman, Jean Botev, Ada Diaconescu, Lukas Esterle, Christian Gruhl, Christopher Landauer, Peter R. Lewis, Phyllis R. Nelson, Anthony Stein, Christopher Stewart, and Sven Tomforde

Workshop Details

2019 IEEE 4th International Workshops on Foundations and Applications of Self* Systems (FAS*W).

Umeå, Sweden.

16th June 2019.


Abstract

Integrated networked systems sense a common environment, learn to navigate the environment and share their experiences. Sharing experiences simplifies learning, reducing costly trial and error in complex environments. However, integration produces dependencies that make constituent systems less robust to failures, unexpected outputs and performance anomalies. Even with APIs and reflective, self-aware techniques, system integration still requires expert programming and tuning. Self-integrating systems proposed in recent research automate integration, but can be challenging to validate at scale. We therefore propose CHARIOT, a common test environment to allow for different approaches and systems to be deployed, assessed and compared on a shared platform for the development of self-integrating systems. In this paper, we discuss the underlying requirements and challenges, potential metrics, and a system metamodel to accommodate these.

“When you believe in things that you don’t understand”: the effect of cross-generational habits on self-improving system integration”

Authors

Chloe M. Barnes, Lukas Esterle and John N. A. Brown

Workshop Details

2019 IEEE 4th International Workshops on Foundations and Applications of Self* Systems (FAS*W).

Umeå, Sweden.

16th June 2019.


Abstract

Humans experiencing unexpected feedback to certain actions which they are not able to explain, might develop superstitious behaviour. In this paper, we discuss that similar behaviour might also occur in engineered systems. We provide a thought-experiment regarding such behaviour in computational systems. In this paper, we propose a first step towards improved runtime systems integration based on a the ability to become aware of previously-unknown others and their actions, as described in networked self-awareness.