Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleApril 2021
Stochastic Approximation on Riemannian Manifolds
Applied Mathematics and Optimization (APMO), Volume 83, Issue 2Pages 1123–1151https://doi.org/10.1007/s00245-019-09581-2AbstractThe standard theory of stochastic approximation (SA) is extended to the case when the constraint set is a Riemannian manifold. Specifically, the standard ODE method for analyzing SA schemes is extended to iterations constrained to stay on a ...
- articleSeptember 2018
An online prediction algorithm for reinforcement learning with linear function approximation using cross entropy method
Machine Language (MALE), Volume 107, Issue 8-10Pages 1385–1429https://doi.org/10.1007/s10994-018-5727-zIn this paper, we provide two new stable online algorithms for the problem of prediction in reinforcement learning, i.e., estimating the value function of a model-free Markov reward process using the linear function approximation architecture and with ...
- articleJune 2018
An incremental off-policy search in a model-free Markov decision process using a single sample path
In this paper, we consider a modified version of the control problem in a model free Markov decision process (MDP) setting with large state and action spaces. The control problem most commonly addressed in the contemporary literature is to find an ...
- articleJanuary 2000
The O.D. E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
SIAM Journal on Control and Optimization (SICON), Volume 38, Issue 2Pages 447–469https://doi.org/10.1137/S0363012997331639It is shown here that stability of the stochastic approximation algorithm is implied by the asymptotic stability of the origin for an associated ODE. This in turn implies convergence of the algorithm. Several specific classes of algorithms are ...