Automatic Recognition of Collective Emergent Behaviours using Behavioural Metrics

S Yang, D Samarasinghe, A Arukgoda… - IEEE …, 2023 - ieeexplore.ieee.org
Collective emergent behaviours are commonly seen in nature such as in flocks of birds and
schools of fish. These behaviours are the results of years of evolution and have been …

Counterfactual learning in enhancing resilience in autonomous agent systems

D Samarasinghe - Frontiers in Artificial Intelligence, 2023 - frontiersin.org
Resilience in autonomous agent systems is about having the capacity to anticipate, respond
to, adapt to, and recover from adverse and dynamic conditions in complex environments. It is …

Grammar‐based autonomous discovery of abstractions for evolution of complex multi‐agent behaviours

D Samarasinghe, M Barlow, E Lakshika… - Swarm and Evolutionary …, 2022 - Elsevier
This paper presents a grammar-based evolutionary approach that facilitates autonomous
discovery of abstractions to learn complex collective behaviours through manageable sub …

A genetic programming-based framework for semi-automated multi-agent systems engineering

N Mc Donnell, J Duggan, E Howley - ACM Transactions on Autonomous …, 2023 - dl.acm.org
With the rise of new technologies, such as Edge computing, Internet of Things, Smart Cities,
and Smart Grids, there is a growing need for multi-agent systems (MAS) approaches …

Efficient CPU-Optimized Parameter Estimation for Modeling Fish Schooling Behavior in Large Particle Systems

S Arabeei, S Subbey - arXiv preprint arXiv:2310.15753, 2023 - arxiv.org
The schooling behavior of fish can be studied through simulations involving a large number
of interacting particles. In such systems, each individual particle is guided by behavior rules …

Competitive Collaboration for Complex Task Learning in Agent Systems

D Samarasinghe, M Barlow, E Lakshika - Australasian Joint Conference …, 2023 - Springer
This paper presents a novel competitive collaboration-based reinforcement learning strategy
to improve the performance of goal-oriented autonomous agent systems. Competitive …