A Near-Optimal Algorithm for Safe Reinforcement Learning Under Instantaneous Hard Constraints.
Ming ShiYingbin LiangNess B. ShroffPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- cost function
- learning algorithm
- optimal solution
- worst case
- dynamic programming
- image processing
- computational efficiency
- optimization algorithm
- np hard
- search space
- computational complexity
- objective function
- computationally efficient
- similarity measure
- benchmark problems
- shortest path problem