Evolutionary Policy Transfer and Search Methods for Boosting Behavior Quality: RoboCup Keep-Away Case Study

Nitschke, Geoff; Didi, Sabre

doi:10.3389/frobt.2017.00062

Cited by 14 publications

(3 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another variation of incremental learning called transfer learning is used in a slightly different context, as the knowledge of the task learned formerly would be subsequently used in learning a related but different task. 18 These concepts have been widely studied in the context of RL, [19][20][21] neuro-evolution 22,23 and genetic programming. 24 There have also been investigations with multi-objective optimisation 25 using incremental learning architectures.…”

Section: Abstraction Learning Architecturesmentioning

confidence: 99%

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

Samarasinghe

Barlow

Lakshika

et al. 2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

This paper presents a grammar‐based evolutionary approach that incorporates abstractions to learn complex collective behaviours through their simpler representations. We propose modifications to the grammar syntax design and genome structure to facilitate evolution of abstractions in separate genome partitions. Two abstraction techniques based on behavioural decomposition and environmental scaffolding are presented to derive these simpler representations. Parallel and incremental learning architectures incorporated with grammatical evolution (GE) are investigated with three complex problems to evaluate their potential in generating collective multi‐agent behaviours. The results infer that both learning architectures surpass a generic GE model in performance for evolving complex behaviours. Furthermore, using environmental scaffolding reduces the robustness of the model than when only the behavioural decomposition technique is used. However, it has more potential to generate solutions with better fitness than when scaffoldings are not used. The evaluations suggest that, by incorporating abstraction learning architectures with grammar‐based evolution can significantly improve the performance of an agent system in complex problem domains.

show abstract

Section: Abstraction Learning Architecturesmentioning

confidence: 99%

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

Samarasinghe

Barlow

Lakshika

et al. 2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

show abstract

“…Keepaway is a subtask of RoboCup that was put forth as a testbed for machine learning in 2001 (Stone & Sutton, 2001). It has since been used for research on temporal difference reinforcement learning with function approximation (Stone, Sutton, & Kuhlmann, 2005), evolutionary learning (Pietro et al, 2002), relational reinforcement learning (Walker et al, 2004), behaviour transfer (Cheng et al, 2018;Didi & Nitschke, 2016a, 2016bNitschke & Didi, 2017;Schwab et al, 2018;, batch reinforcement learning (Riedmiller et al, 2009) and hierarchical reinforcement learning (Bai & Russell, 2017).…”

Section: Robocup Keepaway Soccermentioning

confidence: 99%

A survey of benchmarks for reinforcement learning algorithms

Stapelberg

Malan

2020

SACJ

View full text Add to dashboard Cite

Reinforcement learning has recently experienced increased prominence in the machine learning community. There are many approaches to solving reinforcement learning problems with new techniques developed constantly. When solving problems using reinforcement learning, there are various difficult challenges to overcome. \par To ensure progress in the field, benchmarks are important for testing new algorithms and comparing with other approaches. The reproducibility of results for fair comparison is therefore vital in ensuring that improvements are accurately judged. This paper provides an overview of different contributions to reinforcement learning benchmarking and discusses how they can assist researchers to address the challenges facing reinforcement learning. The contributions discussed are the most used and recent in the literature. The paper discusses the contributions in terms of implementation, tasks and provided algorithm implementations with benchmarks. \par The survey aims to bring attention to the wide range of reinforcement learning benchmarking tasks available and to encourage research to take place in a standardised manner. Additionally, this survey acts as an overview for researchers not familiar with the different tasks that can be used to develop and test new reinforcement learning algorithms.

show abstract

“…Keepaway is a subtask of RoboCup that was put forth as a testbed for machine learning in 2001 [17]. It has since been used for research on temporal difference reinforcement learning with function approximation [46], evolutionary learning [47], relational reinforcement learning [48], behaviour transfer [49,50,51,52,53,54,55], batch reinforcement learning [56] and hierarchical reinforcement learning [57].…”

Section: Robocup Keepaway Soccermentioning

confidence: 99%

A survey of benchmarking frameworks for reinforcement learning

Stapelberg,

Malan

2020

Preprint

View full text Add to dashboard Cite

Reinforcement learning has recently experienced increased prominence in the machine learning community. There are many approaches to solving reinforcement learning problems with new techniques developed constantly. When solving problems using reinforcement learning, there are various difficult challenges to overcome.To ensure progress in the field, benchmarks are important for testing new algorithms and comparing with other approaches. The reproducibility of results for fair comparison is therefore vital in ensuring that improvements are accurately judged. This paper provides an overview of different contributions to reinforcement learning benchmarking and discusses how they can assist researchers to address the challenges facing reinforcement learning. The contributions discussed are the most used and recent in the literature. The paper discusses the contributions in terms of implementation, tasks and provided algorithm implementations with benchmarks.The survey aims to bring attention to the wide range of reinforcement learning benchmarking tasks available and to encourage research to take place in a standardised manner. Additionally, this survey acts as an overview for researchers not familiar with the different tasks that can be used to develop and test new reinforcement learning algorithms.

show abstract

Evolutionary Policy Transfer and Search Methods for Boosting Behavior Quality: RoboCup Keep-Away Case Study

Cited by 14 publications

References 64 publications

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

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

A survey of benchmarks for reinforcement learning algorithms

A survey of benchmarking frameworks for reinforcement learning

Contact Info

Product

Resources

About