Variance-constrained actor-critic algorithms for discounted and average reward MDPs
Open Access
- 5 August 2016
- journal article
- research article
- Published by Springer Nature in Machine Learning
- Vol. 105 (3) , 367-417
Abstract
No abstract availableKeywords
This publication has 46 references indexed in Scilit:
- Stochastic approximation algorithms for constrained optimization via simulationACM Transactions on Modeling and Computer Simulation, 2011
- Risk-averse dynamic programming for Markov decision processesMathematical Programming, 2010
- Adaptive Newton-based multivariate smoothed functional algorithms for simulation optimizationACM Transactions on Modeling and Computer Simulation, 2007
- Adaptive multivariate three-timescale stochastic approximation algorithms for simulation based optimizationACM Transactions on Modeling and Computer Simulation, 2005
- Convergence rate of linear two-time-scale stochastic approximationThe Annals of Applied Probability, 2004
- Two-timescale simultaneous perturbation stochastic approximation using deterministic perturbation sequencesACM Transactions on Modeling and Computer Simulation, 2003
- A Kiefer-Wolfowitz algorithm with randomized differencesIEEE Transactions on Automatic Control, 1999
- Algorithms and Software Tools for IC Yield Optimization Based on Fundamental Fabrication ParametersIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 1986
- Mutual Fund PerformanceThe Journal of Business, 1966
- On general minimax theoremsPacific Journal of Mathematics, 1958