Interior Point Constrained Reinforcement Learning with Global Convergence Guarantees.
Tingting NiMaryam KamgarpourPublished in: CoRR (2023)
Keyphrases
- global convergence
- interior point
- reinforcement learning
- convergence rate
- primal dual
- linear programming
- interior point methods
- global optimum
- convergence speed
- optimization methods
- convergence analysis
- semidefinite programming
- linear program
- convex optimization
- linear programming problems
- nonnegative matrix factorization
- step size
- particle swarm
- machine learning
- objective function
- semidefinite
- linear systems
- optimal solution
- variational inequalities
- simulated annealing
- learning algorithm
- dynamic programming
- search space
- np hard
- neural network
- pso algorithm
- lp relaxation
- particle swarm optimization
- least squares