Below you can find my publications based on chronological order or by topic.
Chronological
Bossens, D. M., & Thomas, P. (2022). Low Variance Off-policy Evaluation with State-based Importance Sampling. ArXiv Preprint. https://arxiv.org/abs/2212.03932
Bossens, D. M., & Evers, C. (2022). Trust in Language Grounding: a new AI challenge for human-robot teams. ArXiv Preprint. http://arxiv.org/abs/2209.02066
Bossens, D. M., & Bishop, N. (2022). Explicit Explore, Exploit, or Escape (E4): near-optimal safety-constrained reinforcement learning in polynomial time. Machine Learning. https://doi.org/10.1007/s10994-022-06201-z
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). https://doi.org/10.1007/s43154-022-00079-4
Bossens, D. M., & Tarapore, D. (2022). Quality-Diversity Meta-Evolution: customising behaviour spaces to a meta-objective. IEEE Transactions on Evolutionary Computation, c, 1–11. https://doi.org/10.1109/TEVC.2022.3152384
Thomas, T., Bossens, D. M., & Tarapore, D. (2021). ASVLite: a high-performance simulator for autonomous surface vehicles. The 2021 International Conference on Robotics and Automation (ICRA 2021). https://dl.acm.org/doi/abs/10.1109/ICRA48506.2021.9561815
Bossens, D. M., & Tarapore, D. (2021). Rapidly adapting robot swarms with Swarm Map-based Bayesian Optimisation. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA 2021), 9848–9854. https://doi.org/10.1109/ICRA48506.2021.9560958
Bossens, D. M., & Tarapore, D. (2021). On the use of feature-maps for improved quality-diversity meta-evolution. Proceedings of the 2021 Genetic and Evolutionary Computation Conference (GECCO 2021) Companion, 83–84. https://doi.org/https://doi.org/10.1145/3449726.3459442
Bossens, D. M., & Tarapore, D. (2021). QED: Using Quality-Environment-Diversity to Evolve Resilient Robot Swarms. IEEE Transactions on Evolutionary Computation, 25(2), 346–357. https://doi.org/10.1109/TEVC.2020.3036578
Bossens, D. M., & Sobey, A. J. (2021). Lifetime policy reuse and the importance of task capacity. ArXiv Preprint. http://arxiv.org/abs/2106.01741
Bossens, D. M. (2020). Reinforcement learning with limited prior knowledge in long-term environments [University of Southampton]. In PhD Thesis. http://eprints.soton.ac.uk/id/eprint/442596
Bossens, D. M., Mouret, J., & Tarapore, D. (2020). Learning behaviour-performance maps with meta-evolution. Genetic and Evolutionary Computation Conference (GECCO 2020), 49–57. https://dl.acm.org/doi/10.1145/3377930.3390181
Bossens, D. M., Townsend, N. C., & Sobey, A. J. (2019). Learning to learn with active adaptive perception. Neural Networks, 115, 30–49. https://doi.org/10.1016/J.NEUNET.2019.03.006
By topic
Evolution
Bossens, D. M., & Tarapore, D. (2022). Quality-Diversity Meta-Evolution: customising behaviour spaces to a meta-objective. IEEE Transactions on Evolutionary Computation, c, 1–11. https://doi.org/10.1109/TEVC.2022.3152384
Bossens, D. M., & Tarapore, D. (2021). On the use of feature-maps for improved quality-diversity meta-evolution. Proceedings of the 2021 Genetic and Evolutionary Computation Conference (GECCO 2021) Companion, 83–84. https://doi.org/https://doi.org/10.1145/3449726.3459442
Bossens, D. M., & Tarapore, D. (2021). QED: Using Quality-Environment-Diversity to Evolve Resilient Robot Swarms. IEEE Transactions on Evolutionary Computation, 25(2), 346–357. https://doi.org/10.1109/TEVC.2020.3036578
Bossens, D. M., Mouret, J., & Tarapore, D. (2020). Learning behaviour-performance maps with meta-evolution. Genetic and Evolutionary Computation Conference (GECCO 2020), 49–57. https://dl.acm.org/doi/10.1145/3377930.339
Reinforcement learning
Meta-RL
Bossens, D. M., & Sobey, A. J. (2021). Lifetime policy reuse and the importance of task capacity. ArXiv Preprint. http://arxiv.org/abs/2106.01741
Bossens, D. M. (2020). Reinforcement learning with limited prior knowledge in long-term environments [University of Southampton]. In PhD Thesis. http://eprints.soton.ac.uk/id/eprint/442596
Bossens, D. M., Townsend, N. C., & Sobey, A. J. (2019). Learning to learn with active adaptive perception. Neural Networks, 115, 30–49. https://doi.org/10.1016/J.NEUNET.2019.03.006
Safe RL
Bossens, D. M., & Thomas, P. (2022). Low Variance Off-policy Evaluation with State-based Importance Sampling. ArXiv Preprint. https://arxiv.org/abs/2212.03932
Bossens, D. M., & Bishop, N. (2022). Explicit Explore, Exploit, or Escape (E4): near-optimal safety-constrained reinforcement learning in polynomial time. Machine Learning. https://doi.org/10.1007/s10994-022-06201-z
Robotics
Bossens, D. M., & Evers, C. (2022). Trust in Language Grounding: a new AI challenge for human-robot teams. ArXiv Preprint. http://arxiv.org/abs/2209.02066
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). https://doi.org/10.1007/s43154-022-00079-4
Thomas, T., Bossens, D. M., & Tarapore, D. (2021). ASVLite: a high-performance simulator for autonomous surface vehicles. The 2021 International Conference on Robotics and Automation (ICRA 2021). https://dl.acm.org/doi/abs/10.1109/ICRA48506.2021.9561815
Bossens, D. M., & Tarapore, D. (2021). Rapidly adapting robot swarms with Swarm Map-based Bayesian Optimisation. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA 2021), 9848–9854. https://doi.org/10.1109/ICRA48506.2021.9560958