Safety-aware Adaptive Reinforcement Learning with Applications to Brushbot Navigation.
Motoya OhnishiLi WangGennaro NotomistaMagnus EgerstedtPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- multi agent
- robot navigation
- learning capabilities
- machine learning
- temporal difference learning
- learning process
- model free
- learning problems
- traffic signal
- stochastic approximation
- robot control
- reinforcement learning algorithms
- function approximation
- real time
- markov decision processes
- monte carlo
- artificial neural networks
- genetic algorithm
- neural network