Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Conferences, Workshops, Symposiums, and Seminars
  4. Budgeted Knowledge Transfer for State-wise Heterogeneous RL Agents
 
Loading...
Thumbnail Image
conference paper

Budgeted Knowledge Transfer for State-wise Heterogeneous RL Agents

Farshidian, Farbod
•
Talebpour, Zeynab  
•
Nili Ahmadabadi, Majid
Huang, Tingwen
•
Zeng, Zhigang
Show more
2012
Neural Information Processing
19th International Conference, ICONIP 2012

In this paper we introduce a budgeted knowledge transfer algorithm for non-homogeneous reinforcement learning agents. Here the source and the target agents are completely identical except in their state representations. The algorithm uses functional space (Q-value space) as the transfer-learning media. In this method, the target agent’s functional points (Q-values) are estimated in an automatically selected lower-dimension subspace in order to accelerate knowledge transfer. The target agent searches that subspace using an exploration policy and selects actions accordingly during the period of its knowledge transfer in order to facilitate gaining an appropriate estimate of its Q-table. We show both analytically and empirically that this method decreases the required learning budget for the target agent.

  • Files
  • Details
  • Metrics
Loading...
Thumbnail Image
Name

KnoweldgeTransfer.pdf

Type

Publisher's Version

Access type

openaccess

Size

218.8 KB

Format

Adobe PDF

Checksum (MD5)

785c2b4efe69e2017c4a293c7f7c1aa2

Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés