Nonconvex Policy Search Using Variational Inequalities.
Yusen ZhanHaitham Bou-AmmarMatthew E. TaylorPublished in: Neural Comput. (2017)
Keyphrases
- policy search
- variational inequalities
- nonlinear programming
- reinforcement learning
- sensitivity analysis
- primal dual
- continuous state
- complementarity problems
- convex sets
- reinforcement learning algorithms
- dynamic programming
- fixed point
- convex optimization
- boundary conditions
- nash equilibrium
- partially observable markov decision processes
- optimization problems
- policy gradient
- saddle point
- reward function
- linear programming
- model free
- total variation
- bayesian networks