RL4HCI: Reinforcement Learning for Humans, Computers, and Interaction.
Dorota GlowackaAndrew HowesJussi P. P. JokinenAntti OulasvirtaÖzgür SimsekPublished in: CHI Extended Abstracts (2021)
Keyphrases
- reinforcement learning
- human computer interaction
- function approximation
- human communication
- interaction design
- model free
- state space
- optimal policy
- temporal difference
- reinforcement learning algorithms
- learning algorithm
- markov decision processes
- solve complex tasks
- human computer
- control problems
- supervised learning
- rl algorithms
- dynamic programming
- turing test
- human computer interface
- direct policy search
- optimal control
- human beings
- machine learning
- computer systems
- learning capabilities
- interface design
- agent learns
- action space
- learning agents
- multi agent
- continuous state and action spaces
- state and action spaces
- policy evaluation
- function approximators
- learning process
- temporal difference learning
- control policy
- gesture recognition
- policy iteration
- complex domains
- transfer learning
- action selection
- hand gestures