5 papers
Robust Markov Decision Processes on Continuous State Spaces
Mengmeng Li, Yifan Hu, Daniel Kuhn +1
We study infinite-horizon robust Markov decision processes (MDPs) on continuous state spaces with structured rectangular ambiguity set. The proposed ambiguity set falls within the…
Multistage Conditional Compositional Optimization
Buse Åen, Yifan Hu, Daniel Kuhn
We introduce Multistage Conditional Compositional Optimization (MCCO) as a new paradigm for decision-making under uncertainty that combines aspects of multistage stochastic program…
Landscape of Policy Optimization for Finite Horizon MDPs with General State and Action
Xin Chen, Yifan Hu, Minda Zhao
Policy gradient methods are widely used in reinforcement learning. Yet, the nonconvexity of policy optimization poses significant challenges in understanding the global convergence…
Stochastic Optimization under Hidden Convexity
Ilyas Fatkhullin, Niao He, Yifan Hu
In this work, we consider constrained stochastic optimization problems under hidden convexity, i.e., those that admit a convex reformulation via non-linear (but invertible) map $c(…
Multi-level Monte-Carlo Gradient Methods for Stochastic Optimization with Biased Oracles
Yifan Hu, Jie Wang, Xin Chen +1
We consider stochastic optimization when one only has access to biased stochastic oracles of the objective and the gradient, and obtaining stochastic gradients with low biases come…