Curriculum Reinforcement Learning via Constrained Optimal Transport.
Pascal KlinkHaoyi YangCarlo D'EramoJan PetersJoni PajarinenPublished in: ICML (2022)
Keyphrases
- reinforcement learning
- optimal control
- dynamic programming
- function approximation
- approximate dynamic programming
- high school
- optimal policy
- machine learning
- cooperative learning
- optimal solution
- software engineering
- worst case
- learning process
- closed form
- case study
- e learning
- information systems
- model free
- optimal design
- control policy
- data sets