Divide-and-Conquer Reinforcement Learning.
Dibya GhoshAvi SinghAravind RajeswaranVikash KumarSergey LevinePublished in: CoRR (2017)
Keyphrases
- reinforcement learning
- function approximation
- model free
- temporal difference
- optimal policy
- robotic control
- multi agent
- machine learning
- state space
- learning algorithm
- real time
- data mining
- reinforcement learning algorithms
- optimal control
- transfer learning
- markov decision processes
- learning problems
- artificial intelligence
- markov chain
- supervised learning
- active learning
- learning process
- temporal difference learning
- stochastic approximation
- continuous state
- transition model
- case study