Mood modelling within reinforcement learning.
Joe CollenetteKatie AtkinsonDaan BloembergenKarl TuylsPublished in: ECAL (2017)
Keyphrases
- reinforcement learning
- function approximation
- state space
- temporal difference
- model free
- optimal policy
- markov decision processes
- policy search
- learning algorithm
- machine learning
- dynamical systems
- direct policy search
- control policy
- function approximators
- action selection
- real time
- sufficient conditions
- dynamic programming
- information retrieval
- real world