Integrating an Observer in Interactive Reinforcement Learning to Learn Legible Trajectories.
Manuel BiedMohamed ChetouaniPublished in: RO-MAN (2020)
Keyphrases
- reinforcement learning
- interactive learning
- function approximation
- reinforcement learning agents
- data sets
- motion patterns
- agent receives
- user friendly
- markov decision processes
- dynamic environments
- learning algorithm
- path planning
- virtual reality
- model free
- temporal difference
- complex domains
- trajectory data
- markov decision process
- function approximators
- moving object trajectories
- machine learning