Robert J. Smith

15 papers A 4B 3Journal 3Unranked 5

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