July 2020

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.