Login / Signup
Scalable Summary-State POMDP Hybrid Dialog System for Multiple Goal Drifting Requests and Massive Slot Entity Instances.
Sangjun Koo
Seonghan Ryu
Kyusong Lee
Gary Geunbae Lee
Published in:
IWSDS (2015)
Keyphrases
</>
state space
reinforcement learning
belief state
neural network
randomly generated
knowledge base
multi agent
natural language processing
optimal policy
named entities
model free reinforcement learning