TY - GEN
T1 - Leveraging human knowledge in tabular Reinforcement learning
T2 - 26th International Joint Conference on Artificial Intelligence, IJCAI 2017
AU - Rosenfeld, Ariel
AU - Taylor, Matthew E.
AU - Kraus, Sarit
N1 - Funding Information: This paper is an extended version of a short AAMAS paper [Rosenfeld et al., 2017]. This research was funded in part by MAFAT. It has also taken place at the Intelligent Robot Learning (IRL) Lab, which is supported in part by NASA NNX16CD07C, NSF IIS-1149917, NSF IIS-1643614, and USDA 2014-67021-22174.
PY - 2017
Y1 - 2017
N2 - Reinforcement Learning (RL) can be extremely effective in solving complex, real-world problems. However, injecting human knowledge into an RL agent may require extensive effort on the human designer's part. To date, human factors are generally not considered in the development and evaluation of possible approaches. In this paper, we propose and evaluate a novel method, based on human psychology literature, which we show to be both effective and efficient, for both expert and non-expert designers, in injecting human knowledge for speeding up tabular RL.
AB - Reinforcement Learning (RL) can be extremely effective in solving complex, real-world problems. However, injecting human knowledge into an RL agent may require extensive effort on the human designer's part. To date, human factors are generally not considered in the development and evaluation of possible approaches. In this paper, we propose and evaluate a novel method, based on human psychology literature, which we show to be both effective and efficient, for both expert and non-expert designers, in injecting human knowledge for speeding up tabular RL.
UR - http://www.scopus.com/inward/record.url?scp=85031929784&partnerID=8YFLogxK
U2 - 10.24963/ijcai.2017/534
DO - 10.24963/ijcai.2017/534
M3 - منشور من مؤتمر
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 3823
EP - 3830
BT - 26th International Joint Conference on Artificial Intelligence, IJCAI 2017
A2 - Sierra, Carles
Y2 - 19 August 2017 through 25 August 2017
ER -