HMM-based Temporal Difference Learning with State Transition Updating for Tracking Human Communicational Behaviors.
Minh Anh Thi HoYoji YamadaYoji UmetaniPublished in: J. Robotics Mechatronics (2003)
Keyphrases
- state transition
- temporal difference learning
- state transitions
- hidden markov models
- finite state machines
- state transition model
- function approximation
- state space
- human behavior
- reinforcement learning
- evaluation function
- black box
- input output
- fixed point
- game playing
- temporal difference
- particle filter
- probability distribution
- markov decision process
- object tracking
- markov chain
- reinforcement learning algorithms
- appearance model
- markov models
- sufficient conditions
- markov decision processes
- neural network