Reinforcement Learning in Multi-Party Trading Dialog.
Takuya HiraokaKallirroi GeorgilaElnaz NouriDavid R. TraumSatoshi NakamuraPublished in: SIGDIAL Conference (2015)
Keyphrases
- multi party
- reinforcement learning
- privacy preserving
- human communication
- state space
- reinforcement learning algorithms
- electronic commerce
- function approximation
- model free
- machine learning
- trading systems
- mental states
- conversational agents
- virtual humans
- description language
- user interface
- natural language
- financial markets
- multi agent
- optimal policy
- domain specific
- mixed initiative
- electronic markets
- conversational agent
- case study