Reward Shaping with Recurrent Neural Networks for Speeding up On-Line Policy Learning in Spoken Dialogue Systems
Keyword(s):
Keyword(s):
2009 ◽
2014 ◽
Vol 21
(1)
◽
pp. 46-51
◽
2005 ◽
Vol 39
(1)
◽
pp. 65-75
◽