dc.contributor.author |
Earle, AC
|
|
dc.contributor.author |
Saxe, AM
|
|
dc.contributor.author |
Rosman, Benjamin S
|
|
dc.date.accessioned |
2018-05-23T06:57:35Z |
|
dc.date.available |
2018-05-23T06:57:35Z |
|
dc.date.issued |
2018-04 |
|
dc.identifier.citation |
Earle, A.C., Saxe, A.M. and Rosman, B.S. 2018. Hierarchical subtask discovery with non-negative matrix factorization. Sixth International Conference on Learning Representations (ICLR2018), 30 April 2018 - 3 May 2018, Vancouver Convention Center, Vancouver, Canada |
en_US |
dc.identifier.uri |
https://iclr.cc/Conferences/2018/Schedule?type=Poster
|
|
dc.identifier.uri |
https://openreview.net/forum?id=ry80wMW0W
|
|
dc.identifier.uri |
http://hdl.handle.net/10204/10228
|
|
dc.description |
Paper presented at the Sixth International Conference on Learning Representations (ICLR2018), 30 April 2018 - 3 May 2018, Vancouver Convention Center, Vancouver, Canada |
en_US |
dc.description.abstract |
Hierarchical reinforcement learning methods offer a powerful means of planning flexible behavior in complicated domains. However, learning an appropriate hierarchical decomposition of a domain into subtasks remains a substantial challenge. We present a novel algorithm for subtask discovery, based on the recently introduced multitask linearly-solvable Markov decision process (MLMDP) framework. The MLMDP can perform never-before-seen tasks by representing them as a linear combination of a previously learned basis set of tasks. In this setting, the subtask discovery problem can naturally be posed as finding an optimal low-rank approximation of the set of tasks the agent will face in a domain. We use non-negative matrix factorization to discover this minimal basis set of tasks, and show that the technique learns intuitive decompositions in a variety of domains. Our method has several qualitatively desirable features: it is not limited to learning subtasks with single goal states, instead learning distributed patterns of preferred states; it learns qualitatively different hierarchical decompositions in the same domain depending on the ensemble of tasks the agent will face; and it may be straightforwardly iterated to obtain deeper hierarchical decompositions. |
en_US |
dc.language.iso |
en |
en_US |
dc.relation.ispartofseries |
Worklist;20912 |
|
dc.subject |
Reinforcement learning |
en_US |
dc.subject |
Subtask discovery |
en_US |
dc.subject |
LMDPs |
en_US |
dc.title |
Hierarchical subtask discovery with non-negative matrix factorization |
en_US |
dc.type |
Conference Presentation |
en_US |
dc.identifier.apacitation |
Earle, A., Saxe, A., & Rosman, B. S. (2018). Hierarchical subtask discovery with non-negative matrix factorization. http://hdl.handle.net/10204/10228 |
en_ZA |
dc.identifier.chicagocitation |
Earle, AC, AM Saxe, and Benjamin S Rosman. "Hierarchical subtask discovery with non-negative matrix factorization." (2018): http://hdl.handle.net/10204/10228 |
en_ZA |
dc.identifier.vancouvercitation |
Earle A, Saxe A, Rosman BS, Hierarchical subtask discovery with non-negative matrix factorization; 2018. http://hdl.handle.net/10204/10228 . |
en_ZA |
dc.identifier.ris |
TY - Conference Presentation
AU - Earle, AC
AU - Saxe, AM
AU - Rosman, Benjamin S
AB - Hierarchical reinforcement learning methods offer a powerful means of planning flexible behavior in complicated domains. However, learning an appropriate hierarchical decomposition of a domain into subtasks remains a substantial challenge. We present a novel algorithm for subtask discovery, based on the recently introduced multitask linearly-solvable Markov decision process (MLMDP) framework. The MLMDP can perform never-before-seen tasks by representing them as a linear combination of a previously learned basis set of tasks. In this setting, the subtask discovery problem can naturally be posed as finding an optimal low-rank approximation of the set of tasks the agent will face in a domain. We use non-negative matrix factorization to discover this minimal basis set of tasks, and show that the technique learns intuitive decompositions in a variety of domains. Our method has several qualitatively desirable features: it is not limited to learning subtasks with single goal states, instead learning distributed patterns of preferred states; it learns qualitatively different hierarchical decompositions in the same domain depending on the ensemble of tasks the agent will face; and it may be straightforwardly iterated to obtain deeper hierarchical decompositions.
DA - 2018-04
DB - ResearchSpace
DP - CSIR
KW - Reinforcement learning
KW - Subtask discovery
KW - LMDPs
LK - https://researchspace.csir.co.za
PY - 2018
T1 - Hierarchical subtask discovery with non-negative matrix factorization
TI - Hierarchical subtask discovery with non-negative matrix factorization
UR - http://hdl.handle.net/10204/10228
ER -
|
en_ZA |