David M. Bossens

Publication Activity (10 Years)

Years Active: 2019-2024
Publications (10 Years): 20

Top Topics

Policy Evaluation

Monte Carlo Localization

Deterministic Domains

Top Venues

IEEE Trans. Evol. Comput.

Publications

David M. Bossens, Adam J. Sobey
Lifetime policy reuse and the importance of task capacity. AI Commun. 37 (1) (2024)
David M. Bossens
Robust Lagrangian and Adversarial Policy Gradient for Robust Constrained Markov Decision Processes. CoRR (2023)
David M. Bossens, Nicholas Bishop
): near-optimal safety-constrained reinforcement learning in polynomial time. Mach. Learn. 112 (3) (2023)
David M. Bossens, Sarvapali D. Ramchurn, Danesh Tarapore
Resilient robot teams: a review integrating decentralised control, change-detection, and learning. CoRR (2022)
David M. Bossens, Philip Thomas
Low Variance Off-policy Evaluation with State-based Importance Sampling. CoRR (2022)
David M. Bossens, Danesh Tarapore
Quality-Diversity Meta-Evolution: Customizing Behavior Spaces to a Meta-Objective. IEEE Trans. Evol. Comput. 26 (5) (2022)
David M. Bossens, Christine Evers
Trust in Language Grounding: a new AI challenge for human-robot teams. CoRR (2022)
David M. Bossens, Danesh Tarapore
Rapidly adapting robot swarms with Swarm Map-based Bayesian Optimisation. ICRA (2021)
David M. Bossens, Danesh Tarapore
On the use of feature-maps and parameter control for improved quality-diversity meta-evolution. CoRR (2021)
David M. Bossens, Danesh Tarapore
Quality-Diversity Meta-Evolution: customising behaviour spaces to a meta-objective. CoRR (2021)
David M. Bossens, Danesh Tarapore
QED: Using Quality-Environment-Diversity to Evolve Resilient Robot Swarms. IEEE Trans. Evol. Comput. 25 (2) (2021)
Toby Thomas, David M. Bossens, Danesh Tarapore
ASVLite: a high-performance simulator for autonomous surface vehicles. ICRA (2021)
David M. Bossens, Adam J. Sobey
Lifetime policy reuse and the importance of task capacity. CoRR (2021)
David M. Bossens, Nicholas Bishop
): near-optimal safety-constrained reinforcement learning in polynomial time. CoRR (2021)
David M. Bossens, Danesh Tarapore
On the use of feature-maps for improved quality-diversity meta-evolution. GECCO Companion (2021)
Toby Thomas, David M. Bossens, Danesh Tarapore
ASV-Swarm: a high-performance simulator for the dynamics of a swarm of autonomous marine vehicles in waves. CoRR (2020)
David M. Bossens, Jean-Baptiste Mouret, Danesh Tarapore
Learning behaviour-performance maps with meta-evolution. GECCO (2020)
David M. Bossens, Danesh Tarapore
QED: using Quality-Environment-Diversity to evolve resilient robot swarms. CoRR (2020)
David M. Bossens, Danesh Tarapore
Rapidly adapting robot swarms with Swarm Map-based Bayesian Optimisation. CoRR (2020)
David M. Bossens, Nicholas C. Townsend, Adam J. Sobey
Learning to learn with active adaptive perception. Neural Networks 115 (2019)