Skill Discovery in Continuous Reinforcement Learning Domains using Skill Chaining

Skill Discovery in Continuous Reinforcement Learning Domains using Skill Chaining. Konidaris, G. & Barreto, A. S
abstract bibtex

We introduce a skill discovery method for reinforcement learning in continuous domains that constructs chains of skills leading to an end-of-task reward. We demonstrate experimentally that it creates appropriate skills and achieves performance beneﬁts in a challenging continuous domain.

@article{konidaris_skill_nodate-1,
	title = {Skill {Discovery} in {Continuous} {Reinforcement} {Learning} {Domains} using {Skill} {Chaining}},
	abstract = {We introduce a skill discovery method for reinforcement learning in continuous domains that constructs chains of skills leading to an end-of-task reward. We demonstrate experimentally that it creates appropriate skills and achieves performance beneﬁts in a challenging continuous domain.},
	language = {en},
	author = {Konidaris, George and Barreto, Andre S},
	pages = {9}
}

Downloads: 0