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

{"_id":"4djGzJFsyuBCZsgoK","bibbaseid":"konidaris-barreto-skilldiscoveryincontinuousreinforcementlearningdomainsusingskillchaining","authorIDs":[],"author_short":["Konidaris, G.","Barreto, A. S"],"bibdata":{"bibtype":"article","type":"article","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":[{"propositions":[],"lastnames":["Konidaris"],"firstnames":["George"],"suffixes":[]},{"propositions":[],"lastnames":["Barreto"],"firstnames":["Andre","S"],"suffixes":[]}],"pages":"9","bibtex":"@article{konidaris_skill_nodate-1,\n\ttitle = {Skill {Discovery} in {Continuous} {Reinforcement} {Learning} {Domains} using {Skill} {Chaining}},\n\tabstract = {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.},\n\tlanguage = {en},\n\tauthor = {Konidaris, George and Barreto, Andre S},\n\tpages = {9}\n}\n\n","author_short":["Konidaris, G.","Barreto, A. S"],"key":"konidaris_skill_nodate-1","id":"konidaris_skill_nodate-1","bibbaseid":"konidaris-barreto-skilldiscoveryincontinuousreinforcementlearningdomainsusingskillchaining","role":"author","urls":{},"downloads":0,"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/asneha213","creationDate":"2019-07-08T00:48:54.932Z","downloads":0,"keywords":[],"search_terms":["skill","discovery","continuous","reinforcement","learning","domains","using","skill","chaining","konidaris","barreto"],"title":"Skill Discovery in Continuous Reinforcement Learning Domains using Skill Chaining","year":null,"dataSources":["fjacg9txEnNSDwee6"]}