MRCDRL: Multi-robot coordination with deep reinforcement learning.
Di WangHongbin DengZhenhua PanPublished in: Neurocomputing (2020)
Keyphrases
- reinforcement learning
- multi robot coordination
- multi robot
- function approximation
- reinforcement learning algorithms
- learning process
- machine learning
- temporal difference
- model free
- optimal control
- multi agent reinforcement learning
- stochastic approximation
- markov decision processes
- path planning
- supervised learning
- state space
- real time
- database
- optimal policy
- learning classifier systems
- bayesian networks
- deep learning
- temporal difference learning
- reinforcement learning methods
- case study
- learning algorithm
- transition model
- direct policy search