Human-Machine Coadaptation Based on Reinforcement Learning with Policy Gradients.
Karim A. TahboubPublished in: ICSC (2019)
Keyphrases
- human machine
- reinforcement learning
- optimal policy
- policy search
- action selection
- markov decision process
- spoken dialog systems
- policy gradient
- control policy
- function approximators
- human operators
- reward function
- human machine interaction
- partially observable
- function approximation
- markov decision processes
- action space
- reinforcement learning algorithms
- spoken dialogue systems
- state space
- temporal difference
- partially observable markov decision processes
- dynamic programming
- multi agent
- model free
- learning algorithm
- artificial neural networks
- computer vision