David Bossens

• PI, Safety and desirability criteria for AI-controlled aerial drones on construction sites, UKRI TASHub

1. Bossens, D. M., & Nitanda, A. Mirror descent policy optimisation for robust constrained markov decision processes. Transactions on Machine Learning Research. J2C Certification. (2025)

2. Hou, Y., Yu, Z., Bossens, D. M., Guo, Z., Wu, Y., Ge, H., & Ong, Y.-S. Evolutionary heterogeneous multitasking for quality diversity optimisation. IEEE Transactions on Evolutionary Computation. (2025)

3. Wan, Z., Yu, X., Bossens, D. M., Lyu, Y., Guo, Q., Fan, F. X., Ong, Y.-S, Tsang, I. W. Diversifying Policy Behaviors with Extrinsic Behavioural Curiosity. In International Conference on Machine Learning (ICML 2025). (2025)

4. Zhao, H., Yu, X., Bossens, D. M., Tsang, I. W., & Gu, Q. Beyond-Expert Performance: Efficient Imitation Learning with Double Exploration. In International Conference on Learning Representations (ICLR 2025). (2025)

5. Yu, X., Wan, Z., Bossens, D. M., Lyu, Y., Guo, Q., & Tsang, I. W. Imitation from diverse behaviours: Wasserstein quality diversity imitation learning with single-step archive exploration. In International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2025). (2025)

6. Krook, J., Bossens, D., Winter, P., Araujo-Estrada, S., Downer, J., & Windsor, S. Mapping the complexity of legal challenges for trustworthy drones on construction sites in the United Kingdom. ACM Journal on Responsible Computing, 1(3), 1-26. (2024)

7. Bossens, D. M., Bharti, K., & Thompson, J. Quantum Policy Gradient in Reproducing Kernel Hilbert Space. In Quantum Technologies in Machine Learning (QTML 2024). (2024)

8. Bossens, D. M., & Thomas, P. Low Variance Off-policy Evaluation with State-based Importance Sampling. In IEEE Conference on Artificial Intelligence (CAI 2024), 871–883. (2024)

9. Bossens, D. M. Robust Lagrangian and Adversarial Policy Gradient for Robust Constrained Markov Decision Processes. In IEEE Conference on Artificial Intelligence (CAI 2024), 1227–1239. (2024)

10. Bossens, D. M., & Sobey, A. J. Lifetime policy reuse and the importance of task capacity. AI Communications, 37, 115–148. (2023)

11. Bossens, D. M. & Bishop, N. Explicit Explore, Exploit, or Escape (E4): near-optimal safety-constrained reinforcement learning in polynomial time. Machine Learning, 112, 817–858. (2023)

12. Bossens, D. M., Ramchurn, S., & Tarapore, D. Resilient robot teams: a review integrating decentralised control, change-detection, and learning. Current Robotics Reports, 3, 85–95. (2022)

13. Bossens, D. M. & Tarapore, D. Quality-Diversity Meta-Evolution: customising behaviour spaces to a meta-objective. IEEE Transactions on Evolutionary Computation, 1171–1181. (2022)

14. Bossens, D.M. & Tarapore, D. On the use of feature-maps for improved quality-diversity meta-evolution. Proceedings of the Genetic and Evolutionary Computation Conference Companion (GECCO 2021), 83–84. (2021)

15. Thomas, T., Bossens, D. M., & Tarapore, D. ASVLite: a high-performance simulator for autonomous surface vehicles. Proceedings of the International Conference on Robotics and Automation (ICRA 2021), 2249–2255. (2021)

16. Bossens, D. M., & Tarapore, D. Rapidly adapting robot swarms with Swarm Map-based Bayesian Optimisation. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA 2021). (2021)

17. Bossens, D. M. & Tarapore, D. QED: Using Quality-Environment-Diversity to Evolve Resilient Robot Swarms. IEEE Transactions on Evolutionary Computation, 25(2), 346–357. (2021)

18. Bossens, D. M., Mouret, J., & Tarapore, D. Learning behaviour-performance maps with meta-evolution. Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2020), 49–57. (2020)

19. Bossens, D. M., Townsend, N. C., & Sobey, A. J. Learning to learn with active adaptive perception. Neural Networks, 115, 30–49. (2019)

• Reviewer at machine learning and AI conferences and journals
• Co-organiser of Safe RL workshop at IJCAI 2022 and IJCAI 2023