18 citations · 39 across the 6 of their papers we have counts for
Showing 2021Show all
3 papers · 1 filter
cs.LG2021★ 3 cited
Explicit Explore, Exploit, or Escape (): near-optimal safety-constrained reinforcement learning in polynomial time
David M. Bossens, Nicholas Bishop
In reinforcement learning (RL), an agent must explore an initially unknown environment in order to learn a desired behaviour. When RL agents are deployed in real world environments…
cs.NE2021★ 9 cited
Quality-Diversity Meta-Evolution: customising behaviour spaces to a meta-objective
David M. Bossens, Danesh Tarapore
Quality-Diversity (QD) algorithms evolve behaviourally diverse and high-performing solutions. To illuminate the elite solutions for a space of behaviours, QD algorithms require the…
cs.NE2021
On the use of feature-maps and parameter control for improved quality-diversity meta-evolution
David M. Bossens, Danesh Tarapore
In Quality-Diversity (QD) algorithms, which evolve a behaviourally diverse archive of high-performing solutions, the behaviour space is a difficult design choice that should be tai…