A Near-Optimal Algorithm for Safe Reinforcement Learning Under Instantaneous Hard Constraints.
Ming ShiYingbin LiangNess B. ShroffPublished in: ICML (2023)
Keyphrases
- objective function
- cost function
- optimal solution
- linear programming
- optimization problems
- reinforcement learning
- genetic algorithm
- search algorithm
- computational complexity
- state space
- simulated annealing
- np hard
- hard constraints
- benchmark problems
- higher order
- worst case
- dynamic programming
- similarity measure
- learning algorithm