POMDP: POMDP-based user-adaptive decision-making for social robots.
Gonçalo S. MartinsHend Al TairLuís SantosJorge DiasPublished in: Pattern Recognit. Lett. (2019)
Keyphrases
- decision making
- partially observable markov decision processes
- reinforcement learning
- partially observable
- partially observable markov decision process
- finite state
- state space
- dynamical systems
- model free reinforcement learning
- belief state
- optimal policy
- hidden state
- user interaction
- decision makers
- belief space
- continuous state
- end users
- markov decision processes
- point based value iteration
- mobile robot
- multi agent
- dec pomdps
- human friendly
- user interface
- reward function
- recommender systems
- social media
- multi robot
- decision problems
- robot navigation
- autonomous robots
- decision process
- social relationships
- humanoid robot
- cooperative
- markov decision problems
- robotic systems
- path planning
- dynamic programming
- dynamic environments
- markov chain
- machine learning