Robert J. Smith

According to our database, Robert J. Smith authored at least 15 papers between 2016 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Interpreting Tangled Program Graphs Under Partially Observable Dota 2 Invoker Tasks.

Robert J. Smith, Malcolm I. Heywood

IEEE Trans. Artif. Intell., April, 2024

Emergent Braitenberg-style Behaviours for Navigating the ViZDoom 'My Way Home' Labyrinth.

Caleidgh Bayer, Robert J. Smith, Malcolm I. Heywood

CoRR, 2024

2022

Benchmarking genetic programming in a multi-action reinforcement learning locomotion task.

Ryan Amaral, Alexandru Ianta, Caleidgh Bayer, Robert J. Smith, Malcolm I. Heywood

Proceedings of the GECCO '22: Genetic and Evolutionary Computation Conference, Companion Volume, Boston, Massachusetts, USA, July 9, 2022

2021

Emergent Tangled Program Graphs in Partially Observable Recursive Forecasting and ViZDoom Navigation Tasks.

Stephen Kelly, Robert J. Smith, Malcolm I. Heywood, Wolfgang Banzhaf

ACM Trans. Evol. Learn. Optim., 2021

Finding Simple Solutions to Multi-Task Visual Reinforcement Learning Problems with Tangled Program Graphs.

Caleidgh Bayer, Ryan Amaral, Robert J. Smith, Alexandru Ianta, Malcolm I. Heywood

Proceedings of the Genetic Programming Theory and Practice XVIII [GPTP 2021]., 2021

On the impact of tangled program graph marking schemes under the atari reinforcement learning benchmark.

Alexandru Ianta, Ryan Amaral, Caleidgh Bayer, Robert J. Smith, Malcolm I. Heywood

Proceedings of the GECCO '21: Genetic and Evolutionary Computation Conference, 2021

Evolving Simple Solutions to the CIFAR-10 Benchmark using Tangled Program Graphs.

Robert J. Smith, Ryan Amaral, Malcolm I. Heywood

Proceedings of the IEEE Congress on Evolutionary Computation, 2021

2019

Evolving a Dota 2 Hero Bot with a Probabilistic Shared Memory Model.

Robert J. Smith, Malcolm I. Heywood

Proceedings of the Genetic Programming Theory and Practice XVII [GPTP 2019, 2019

Evolving dota 2 shadow fiend bots using genetic programming with external memory.

Robert J. Smith, Malcolm I. Heywood

Proceedings of the Genetic and Evolutionary Computation Conference, 2019

A Model of External Memory for Navigation in Partially Observable Visual Reinforcement Learning Tasks.

Robert J. Smith, Malcolm I. Heywood

Proceedings of the Genetic Programming - 22nd European Conference, 2019

2018

Emergent Policy Discovery for Visual Reinforcement Learning Through Tangled Program Graphs: A Tutorial.

Stephen Kelly, Robert J. Smith, Malcolm I. Heywood

Proceedings of the Genetic Programming Theory and Practice XVI, 2018

Scaling Tangled Program Graphs to Visual Reinforcement Learning in ViZDoom.

Robert J. Smith, Malcolm I. Heywood

Proceedings of the Genetic Programming - 21st European Conference, 2018

2017

Coevolving deep hierarchies of programs to solve complex tasks.

Robert J. Smith, Malcolm I. Heywood

Proceedings of the Genetic and Evolutionary Computation Conference, 2017

2016

Initiating a Moving Target Network Defense with a Real-time Neuro-evolutionary Detector.

Robert J. Smith, Ayse Nur Zincir-Heywood, Malcolm I. Heywood, John T. Jacobs

Proceedings of the Genetic and Evolutionary Computation Conference, 2016

Discovering Rubik's Cube Subgroups using Coevolutionary GP: A Five Twist Experiment.

Robert J. Smith, Stephen Kelly, Malcolm I. Heywood

Proceedings of the 2016 on Genetic and Evolutionary Computation Conference, Denver, CO, USA, July 20, 2016