Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms.
Akifumi WachiWataru HashimotoXun ShenKazumune HashimotoPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- learning algorithm
- orders of magnitude
- recently developed
- data sets
- data structure
- computational cost
- efficient optimization
- model free
- computationally efficient
- machine learning
- dynamic programming
- worst case
- computational complexity
- theoretical analysis
- objective function
- bayesian networks
- search strategies
- function approximation
- neural network