Inverse Constraint Learning and Generalization by Transferable Reward Decomposition.
Jaehwi JangMinjae SongDaehyung ParkPublished in: IEEE Robotics Autom. Lett. (2024)
Keyphrases
- reinforcement learning
- learning algorithm
- prior knowledge
- inductive inference
- learning scheme
- online learning
- learning machines
- supervised learning
- learning systems
- incremental learning
- empirical studies
- learning opportunities
- inductive learning
- learning tasks
- intelligent tutoring systems
- data sets
- knowledge acquisition
- dynamic programming
- case study
- neural network