Robert J. Smith

Publication Activity (10 Years)

Years Active: 2016-2024
Publications (10 Years): 15

Top Topics

Reinforcement Learning

External Memory

Top Venues

GECCO (Companion)

Publications

Robert J. Smith, Malcolm I. Heywood
Interpreting Tangled Program Graphs Under Partially Observable Dota 2 Invoker Tasks. IEEE Trans. Artif. Intell. 5 (4) (2024)
Caleidgh Bayer, Robert J. Smith, Malcolm I. Heywood
Emergent Braitenberg-style Behaviours for Navigating the ViZDoom 'My Way Home' Labyrinth. CoRR (2024)
Ryan Amaral, Alexandru Ianta, Caleidgh Bayer, Robert J. Smith, Malcolm I. Heywood
Benchmarking genetic programming in a multi-action reinforcement learning locomotion task. GECCO Companion (2022)
Stephen Kelly, Robert J. Smith, Malcolm I. Heywood, Wolfgang Banzhaf
Emergent Tangled Program Graphs in Partially Observable Recursive Forecasting and ViZDoom Navigation Tasks. ACM Trans. Evol. Learn. Optim. 1 (3) (2021)
Alexandru Ianta, Ryan Amaral, Caleidgh Bayer, Robert J. Smith, Malcolm I. Heywood
On the impact of tangled program graph marking schemes under the atari reinforcement learning benchmark. GECCO (2021)
Robert J. Smith, Ryan Amaral, Malcolm I. Heywood
Evolving Simple Solutions to the CIFAR-10 Benchmark using Tangled Program Graphs. CEC (2021)
Caleidgh Bayer, Ryan Amaral, Robert J. Smith, Alexandru Ianta, Malcolm I. Heywood
Finding Simple Solutions to Multi-Task Visual Reinforcement Learning Problems with Tangled Program Graphs. GPTP (2021)
Robert J. Smith, Malcolm I. Heywood
Evolving a Dota 2 Hero Bot with a Probabilistic Shared Memory Model. GPTP (2019)
Robert J. Smith, Malcolm I. Heywood
Evolving dota 2 shadow fiend bots using genetic programming with external memory. GECCO (2019)
Robert J. Smith, Malcolm I. Heywood
A Model of External Memory for Navigation in Partially Observable Visual Reinforcement Learning Tasks. EuroGP (2019)
Robert J. Smith, Malcolm I. Heywood
Scaling Tangled Program Graphs to Visual Reinforcement Learning in ViZDoom. EuroGP (2018)
Stephen Kelly, Robert J. Smith, Malcolm I. Heywood
Emergent Policy Discovery for Visual Reinforcement Learning Through Tangled Program Graphs: A Tutorial. GPTP (2018)
Robert J. Smith, Malcolm I. Heywood
Coevolving deep hierarchies of programs to solve complex tasks. GECCO (2017)
Robert J. Smith, Stephen Kelly, Malcolm I. Heywood
Discovering Rubik's Cube Subgroups using Coevolutionary GP: A Five Twist Experiment. GECCO (2016)
Robert J. Smith, Ayse Nur Zincir-Heywood, Malcolm I. Heywood, John T. Jacobs
Initiating a Moving Target Network Defense with a Real-time Neuro-evolutionary Detector. GECCO (Companion) (2016)