QED: using Quality-Environment-Diversity to evolve resilient robot swarms DM Bossens, D Tarapore IEEE Transactions on Evolutionary Computation 25 (2), 346-357, 2020 | 18 | 2020 |
Learning behaviour-performance maps with meta-evolution DM Bossens, JB Mouret, D Tarapore Proceedings of the 2020 Genetic and Evolutionary Computation Conference, 49-57, 2020 | 18 | 2020 |
Rapidly adapting robot swarms with Swarm Map-based Bayesian Optimisation DM Bossens, D Tarapore 2021 IEEE International Conference on Robotics and Automation (ICRA), 9848-9854, 2021 | 14 | 2021 |
Learning to learn with active adaptive perception DM Bossens, NC Townsend, AJ Sobey Neural Networks 115, 30-49, 2019 | 9 | 2019 |
Quality-Diversity Meta-Evolution: customising behaviour spaces to a meta-objective DM Bossens, D Tarapore IEEE Transactions on Evolutionary Computation, 2022 | 6 | 2022 |
Explicit Explore, Exploit, or Escape (): near-optimal safety-constrained reinforcement learning in polynomial time DM Bossens, N Bishop Machine Learning, 1-42, 2022 | 4 | 2022 |
Resilient robot teams: a review integrating decentralised control, change-detection, and learning DM Bossens, S Ramchurn, D Tarapore Current Robotics Reports, 2022 | 3 | 2022 |
Lifetime policy reuse and the importance of task capacity DM Bossens, AJ Sobey arXiv preprint arXiv:2106.01741, 2021 | 3 | 2021 |
ASVLite: a high-performance simulator for autonomous surface vehicles T Thomas, DM Bossens, D Tarapore 2021 IEEE International Conference on Robotics and Automation (ICRA), 2249-2255, 2021 | 2 | 2021 |
On the use of feature-maps and parameter control for improved quality-diversity meta-evolution DM Bossens, D Tarapore arXiv preprint arXiv:2105.10317, 2021 | 2 | 2021 |
Robust Lagrangian and Adversarial Policy Gradient for Robust Constrained Markov Decision Processes DM Bossens arXiv preprint arXiv:2308.11267, 2023 | | 2023 |
Low Variance Off-policy Evaluation with State-based Importance Sampling DM Bossens, P Thomas arXiv preprint arXiv:2212.03932, 2022 | | 2022 |
Trust in Language Grounding: a new AI challenge for human-robot teams DM Bossens, C Evers arXiv preprint arXiv:2209.02066, 2022 | | 2022 |
On the use of feature-maps for improved quality-diversity meta-evolution DM Bossens, D Tarapore Proceedings of the Genetic and Evolutionary Computation Conference Companion …, 2021 | | 2021 |
Reinforcement learning with limited prior knowledge in long-term environments D Bossens University of Southampton, 2020 | | 2020 |