Conference item
Hierarchy through composition with multitask LMDPs
- Abstract:
-
Hierarchical architectures are critical to the scalability of reinforcement learning methods. Most current hierarchical frameworks execute actions serially, with macro-actions comprising sequences of primitive actions. We propose a novel alternative to these control hierarchies based on concurrent execution of many actions in parallel. Our scheme exploits the guaranteed concurrent compositionality provided by the linearly solvable Markov decision process (LMDP) framework, which naturally enab...
Expand abstract
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Preview, Version of record, 2.1MB, Terms of use)
-
- Publication website:
- http://proceedings.mlr.press/v70/saxe17a.html
Authors
Bibliographic Details
- Publisher:
- Journal of Machine Learning Research
- Host title:
- Proceedings of the 34 th International Conference on Machine Learning
- Journal:
- Proceedings of Machine Learning Research More from this journal
- Volume:
- 70
- Issue:
- 2017
- Publication date:
- 2017-08-11
- Acceptance date:
- 2017-03-01
- Event title:
- International Conference on Machine Learning
- Event location:
- Sydney, Australia
- Event website:
- https://icml.cc/Conferences/2017
- Event start date:
- 2017-08-07
- Event end date:
- 2017-08-11
- ISSN:
-
2640-3498
Item Description
- Language:
-
English
- Keywords:
- Pubs id:
-
1115535
- Local pid:
-
pubs:1115535
- Deposit date:
-
2020-07-02
Terms of use
- Copyright holder:
- Saxe et al.
- Copyright date:
- 2017
- Rights statement:
- Copyright 2017 by the author(s).
- Notes:
- This paper was presented at the 34th International Conference on Machine Learning, 7th-11th August 2017, Sydney, Australia.
Metrics
If you are the owner of this record, you can report an update to it here: Report update to this record