Bayesian Model-Based Offline Reinforcement Learning for Product Allocation.
Porter JenkinsHua WeiJ. Stockton JenkinsZhenhui LiPublished in: AAAI (2022)
Keyphrases
- reinforcement learning
- model free
- function approximation
- data driven
- reinforcement learning algorithms
- life cycle
- real time
- maximum likelihood
- resource allocation
- bayesian methods
- bayesian inference
- bayesian estimation
- learning process
- learning algorithm
- optimal allocation
- allocation problems
- product quality
- action selection
- markov decision processes
- multi agent
- genetic algorithm
- production planning
- temporal difference
- optimal control
- bayesian learning
- product design
- product development
- transition model
- dynamic allocation
- neural network