A Two-Tier User Simulation Model for Reinforcement Learning of Adaptive Referring Expression Generation Policies.
Srinivasan JanarthanamOliver LemonPublished in: SIGDIAL Conference (2009)
Keyphrases
- simulation model
- reinforcement learning
- simulation models
- agent based simulation
- discrete event
- optimal policy
- simulation environment
- mathematical model
- recommender systems
- markov decision process
- user preferences
- policy search
- machine learning
- simulation tool
- analytical model
- function approximation
- user experience
- relevance feedback
- state space
- user interface
- user model
- human users
- temporal difference
- markov decision processes
- reward function
- user interaction
- collaborative filtering
- control system
- multi agent