Bridging Scenarios in Reinforcement Learning with Continuously Generated Relaying Predictive Models.
Kuo LiQing-Shan JiaPublished in: CASE (2022)
Keyphrases
- reinforcement learning
- real time
- predictive model
- complex systems
- model free
- automatically generated
- probabilistic model
- predictive modeling
- markov models
- base station
- function approximation
- bayesian framework
- experimental data
- statistical model
- process model
- supervised learning
- dynamic programming
- prior knowledge
- multi agent
- bayesian networks
- information systems
- real world
- neural network