Conference item
Tuning mixed input hyperparameters on the fly for efficient population based AutoRL
- Abstract:
-
Despite a series of recent successes in reinforcement learning (RL), many RL algorithms remain sensitive to hyperparameters. As such, there has recently been interest in the field of AutoRL, which seeks to automate design decisions to create more general algorithms. Recent work suggests that population based approaches may be effective AutoRL algorithms, by learning hyperparameter schedules on the fly. In particular, the PB2 algorithm is able to achieve strong performance in RL tasks by formu...
Expand abstract
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Accepted manuscript, pdf, 3.1MB)
-
Authors
Bibliographic Details
- Publisher:
- Curran Associates Publisher's website
- Host title:
- Advances in Neural Information Processing Systems 34 (NeurIPS 2021)
- Volume:
- 19
- Pages:
- 15513-15528
- Publication date:
- 2022-05-01
- Acceptance date:
- 2021-09-28
- Event title:
- 35th Conference on Neural Information Processing Systems (NeurIPS 2021)
- Event location:
- Virtual event
- Event website:
- https://nips.cc/Conferences/2021/
- Event start date:
- 2021-12-06
- Event end date:
- 2021-12-14
- ISSN:
-
1049-5258
- ISBN:
- 9781713845393
Item Description
- Language:
- English
- Keywords:
- Pubs id:
-
1265403
- Local pid:
- pubs:1265403
- Deposit date:
- 2023-01-20
Terms of use
- Copyright holder:
- Parker-Holder et al and NeurIPS
- Copyright date:
- 2021
- Rights statement:
- Copyright © (2021) by individual authors and Neural Information Processing Systems Foundation Inc. All rights reserved.
- Notes:
- This is the accepted manuscript version of the paper. The final version is available from the Neural Information Processing Systems Foundation at: https://proceedings.neurips.cc/paper/2021/hash/82debd8a12b498e765a11a8e51159440-Abstract.html
Metrics
If you are the owner of this record, you can report an update to it here: Report update to this record