Difference of Convex Functions Programming for Policy Optimization in Reinforcement Learning.
Akshat KumarPublished in: AAMAS (2024)
Keyphrases
- convex functions
- reinforcement learning
- quasiconvex
- convex programming
- optimal policy
- convex programs
- global optimality
- linear program
- objective function
- exact penalty
- policy search
- markov decision process
- convex sets
- dc programming
- primal dual
- function approximation
- function approximators
- linear programming
- optimization problems
- piecewise linear
- global optimization
- markov decision processes
- convex optimization
- action selection
- reinforcement learning algorithms
- supervised learning
- dynamic programming
- special case
- evolutionary algorithm
- optimal solution