Developing Cooperative Policies for Multi-Stage Reinforcement Learning Tasks.
Jordan ErskineChristopher F. LehnertPublished in: IEEE Robotics Autom. Lett. (2022)
Keyphrases
- learning tasks
- multistage
- cooperative
- optimal policy
- reinforcement learning
- transfer learning
- machine learning
- learning algorithm
- learning experience
- supervised learning
- production system
- single stage
- learning problems
- dynamic programming
- multi task
- multi task learning
- function approximation
- lot sizing
- multitask learning
- machine learning algorithms
- markov decision processes
- kernel methods
- average cost
- multi label
- assembly systems
- knowledge discovery
- kernel based learning methods
- data sets
- infinite horizon
- e learning
- support vector machine
- state space