A Caltech Library Service

Co-training for Policy Learning

Song, Jialin and Lanka, Ravi and Yue, Yisong and Ono, Masahiro (2019) Co-training for Policy Learning. . (Unpublished)

[img] PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


We study the problem of learning sequential decision-making policies in settings with multiple state-action representations. Such settings naturally arise in many domains, such as planning (e.g., multiple integer programming formulations) and various combinatorial optimization problems (e.g., those with both integer programming and graph-based formulations). Inspired by the classical co-training framework for classification, we study the problem of co-training for policy learning. We present sufficient conditions under which learning from two views can improve upon learning from a single view alone. Motivated by these theoretical insights, we present a meta-algorithm for co-training for sequential decision making. Our framework is compatible with both reinforcement learning and imitation learning. We validate the effectiveness of our approach across a wide range of tasks, including discrete/continuous control and combinatorial optimization.

Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription Paper
Yue, Yisong0000-0001-9127-1989
Additional Information:The work was funded in part by NSF awards #1637598 & #1645832, and support from Raytheon and Northrop Grumman. This research was also conducted in part at the Jet Propulsion Lab, California Insitute of Technology under a contract with the National Aeronautics and Space Administration.
Funding AgencyGrant Number
Raytheon CompanyUNSPECIFIED
Northrop Grumman CorporationUNSPECIFIED
Record Number:CaltechAUTHORS:20190905-154310582
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:98459
Deposited By: George Porter
Deposited On:05 Sep 2019 23:11
Last Modified:03 Oct 2019 21:41

Repository Staff Only: item control page