Exploiting abstractions for grammar‐based learning of complex multi‐agent behaviours

Samarasinghe, Dilini; Barlow, Michael; Lakshika, Erandi; Kasmarik, Kathryn

doi:10.1002/int.22550

Cited by 4 publications

(3 citation statements)

References 44 publications

(59 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Self-learning adaptive dynamic programming [30] is also experimented in this regard as a means of eliminating the explicit external reward scheme by encouraging agents to learn internal rewards dynamically based on the problem presented. The use of abstractions or modular RL is another approach to solve complex problems through tasks being subdivided into multiple simpler modules to be learned independently and combined [31]- [34].…”

Section: Related Workmentioning

confidence: 99%

Flow-Based Reinforcement Learning

2022

Self Cite

View full text Add to dashboard Cite

This paper presents a novel Flow-based reinforcement learning strategy to model agent systems that can adapt to complex and dynamic problem environments by incrementally mastering their skills. It is inspired by the psychological notion of Flow that describes the optimal mental state experienced by an individual when they are fully immersed in a task and find it intrinsically rewarding to engage with. The proposed model presents an algorithm to describe the Flow experience such that agents can be trained through finer distinctions to the challenges across training time to maintain them in the Flow zone. In contrast to the traditional and incremental learning approaches that suffer from limitations associated with overfitting, the Flow-based model drives agent behaviours not simply through external goals but also through intrinsic curiosity to improve their skills and thus the performance levels. Experimental evaluations are conducted across two simulation environments on a maze navigation task and a reward collection task with comparisons against a generic reinforcement learning model and an incremental reinforcement learning model. The results reveal that these two models are prone to overfit under different design decisions and loose the ability to perform in dynamic variations of the tasks in varying degrees. Conversely, the proposed Flow-based model is capable of achieving near optimal solutions with random environmental factors, appropriately utilising the previously learned knowledge to identify robust solutions to complex problems.

show abstract

Section: Related Workmentioning

confidence: 99%

Flow-Based Reinforcement Learning

2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…In a recent study [11,12] we introduced a GE-based mechanism to synthesise multi-agent behaviours for a homogeneous system, which is capable of reducing human intervention in the rule generation process. In contrast to homogeneous agents, heterogeneous agent rules can complicate the process of learning as the search space for rules becomes proportional to the number of agents in the system increasing the complexity [10].…”

Section: Introductionmentioning

confidence: 99%

Grammar-based cooperative learning for evolving collective behaviours in multi-agent systems

Samarasinghe

Barlow

Lakshika

et al. 2022

Swarm and Evolutionary Computation

View full text Add to dashboard Cite

“…Grammatical Evolution (GE) [19] is an evolutionary computing technique with the unique ability to represent its solution space in the form of programs (tree structures), utilising a context-free grammar (CFG) to define their syntax. We have previously studied GE in consensus based environments for automatically synthesising cooperative behaviours [23,24]. In this paper, we investigate GE in automatic emergence of task allocation within a distributed learning environment by addressing the limitations of the existing IVA modeling techniques that limit human comprehension and explainability of the solutions.…”

mentioning

confidence: 99%

Task Allocation in Multi-Agent Systems with Grammar-Based Evolution

Samarasinghe

Barlow

Lakshika

et al. 2021

Proceedings of the 21th ACM International Conference on Intelligent Virtual Agents

View full text Add to dashboard Cite

This paper presents a grammar-based evolutionary model to facilitate autonomous emergence of task allocation for intelligent multi-agent systems. The approach adopts a context-free grammar to determine the behaviour rule syntax. This allows for flexibility in evolving task allocation under multiple and dynamic constraints without manual rule design and parameter tuning. Experimental evaluations conducted with a target discovery simulation illustrate that the grammar-based model performs successfully in both dynamic and non-dynamic conditions. A statistically significant performance improvement is shown compared to an algorithm developed with the broadcast of local eligibility mechanism and a genetic programming mechanism. Grammatical evolution can achieve near-optimal solutions under restrictions applied on the number of agents, targets and the time allowed. Further, analysis of the evolved rule structures shows that grammatical evolution can identify less complex rule structures for behaviours while maintaining the expected level of performance. The results infer that the proposed model is a promising alternative for dynamic task allocation with human interactions in complex real-world domains.

show abstract

Exploiting abstractions for grammar‐based learning of complex multi‐agent behaviours

Cited by 4 publications

References 44 publications

Flow-Based Reinforcement Learning

Flow-Based Reinforcement Learning

Grammar-based cooperative learning for evolving collective behaviours in multi-agent systems

Task Allocation in Multi-Agent Systems with Grammar-Based Evolution

Contact Info

Product

Resources

About