IRDA: Incremental Reinforcement Learning for Dynamic Resource Allocation.
Jia WangJiannong CaoSenzhang WangZhongyu YaoWengen LiPublished in: IEEE Trans. Big Data (2022)
Keyphrases
- dynamic resource allocation
- reinforcement learning
- resource allocation
- state space
- incremental learning
- function approximation
- allocation policies
- reinforcement learning algorithms
- transfer learning
- markov decision processes
- robotic control
- data sets
- model free
- learning process
- multi agent
- artificial intelligence
- direct policy search
- incremental version
- policy search
- transition model
- stochastic approximation
- temporal difference learning
- control problems
- learning problems
- optimal policy
- search algorithm
- data mining