Reinforcement Learning of Dialogue Coherence and Relevance.
Sultan AlahmariTommy YuanDaniel KudenkoPublished in: CMNA@PERSUASIVE (2019)
Keyphrases
- reinforcement learning
- function approximation
- human machine
- information retrieval
- learning algorithm
- dialogue system
- state space
- machine learning
- mixed initiative
- man machine
- relevance feedback
- spoken dialogue systems
- dynamic programming
- natural language
- markov decision processes
- temporal difference
- multi agent
- multi agent reinforcement learning
- conversational agent
- transition model
- temporal difference learning
- robotic control
- learning problems
- reinforcement learning methods
- policy search
- interactive systems
- reinforcement learning algorithms
- ranked list
- data sets
- test collection
- optimal policy
- supervised learning
- learning process
- genetic algorithm
- neural network