TY - GEN
T1 - Cross-Domain Transfer in Reinforcement Learning Using Target Apprentice
AU - Joshi, Girish
AU - Chowdhary, Girish
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/9/10
Y1 - 2018/9/10
N2 - In this paper, we present a new approach to transfer in Reinforcement Learning (RL) for cross-domain tasks. Unlike, available transfer approaches, where target task learning is accelerated through initialized learning from source, we propose to adapt and reuse the optimal source policy directly in the related domains. We show the optimal policy from a related source task can be near optimal in target domain provided an adaptive policy accounts for the model error between target and the projected source. A significant advantage of the proposed policy augmentation is in generalizing the policies across related domains without having to re-Iearn the new tasks. We demonstrate that, this architecture leads to better sample efficiency in the transfer, reducing sample complexity of target task learning to target apprentice learning.
AB - In this paper, we present a new approach to transfer in Reinforcement Learning (RL) for cross-domain tasks. Unlike, available transfer approaches, where target task learning is accelerated through initialized learning from source, we propose to adapt and reuse the optimal source policy directly in the related domains. We show the optimal policy from a related source task can be near optimal in target domain provided an adaptive policy accounts for the model error between target and the projected source. A significant advantage of the proposed policy augmentation is in generalizing the policies across related domains without having to re-Iearn the new tasks. We demonstrate that, this architecture leads to better sample efficiency in the transfer, reducing sample complexity of target task learning to target apprentice learning.
UR - http://www.scopus.com/inward/record.url?scp=85061246057&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85061246057&partnerID=8YFLogxK
U2 - 10.1109/ICRA.2018.8462977
DO - 10.1109/ICRA.2018.8462977
M3 - Conference contribution
AN - SCOPUS:85061246057
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 7525
EP - 7532
BT - 2018 IEEE International Conference on Robotics and Automation, ICRA 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 IEEE International Conference on Robotics and Automation, ICRA 2018
Y2 - 21 May 2018 through 25 May 2018
ER -