Reinforcement Learning of Multi-Party Trading Dialog Policies.
Takuya HiraokaKallirroi GeorgilaElnaz NouriDavid R. TraumSatoshi NakamuraPublished in: Inf. Media Technol. (2016)
Keyphrases
- multi party
- reinforcement learning
- optimal policy
- policy search
- privacy preserving
- markov decision process
- control policies
- reward function
- fitted q iteration
- partially observable markov decision processes
- electronic commerce
- function approximation
- markov decision processes
- state space
- policy gradient methods
- markov decision problems
- model free
- reinforcement learning algorithms
- dynamic programming
- reinforcement learning agents
- control policy
- learning algorithm
- mental states
- mixed initiative
- multi agent
- temporal difference
- description language
- multi issue
- virtual humans
- conversational agent
- human communication
- fair exchange