Safe Stochastic Model-Based Policy Iteration with Chance Constraints.
Lijing ZhaiKyriakos G. VamvoudakisJérôme HuguesPublished in: CDC (2023)
Keyphrases
- chance constraints
- policy iteration
- model free
- chance constrained
- markov decision processes
- sample path
- reinforcement learning
- stochastic programming
- robust optimization
- fixed point
- least squares
- optimal policy
- temporal difference
- knapsack problem
- function approximation
- computationally tractable
- finite state
- markov decision process
- multistage
- state space
- optimal control
- reverse logistics
- infinite horizon
- convergence rate
- monte carlo
- dynamic programming
- cost function
- average cost
- belief propagation