Search Results for author:
Found 10 papers, 1 papers with code
QCQP-Net: Reliably Learning Feasible Alternating Current Optimal Power Flow Solutions Under Constraints
At the heart of power system operations, alternating current optimal power flow (ACOPF) studies the generation of electric power in the most economical way under network-wide load requirement, and can be formulated as a highly structured non-convex quadratically constrained quadratic program (QCQP).
Learning Payment-Free Resource Allocation Mechanisms
We consider the design of mechanisms that allocate limited resources among self-interested agents using neural networks.
Sequential Fair Resource Allocation under a Markov Decision Process Framework
We propose a new algorithm, SAFFE, that makes fair allocations with respect to the entire demands revealed over the horizon by accounting for expected future demands at each arrival time.
Regularized Gradient Descent Ascent for Two-Player Zero-Sum Markov Games
We study the problem of finding the Nash equilibrium in a two-player zero-sum Markov game.
A Reinforcement Learning Approach to Parameter Selection for Distributed Optimal Power Flow
We train our RL policy using deep Q-learning, and show that this policy can result in significantly accelerated convergence (up to a 59% reduction in the number of iterations compared to existing, curvature-informed penalty parameter selection methods).
Finite-Time Complexity of Online Primal-Dual Natural Actor-Critic Algorithm for Constrained Markov Decision Processes
To solve this constrained optimization program, we study an online actor-critic variant of a classic primal-dual method where the gradients of both the primal and dual functions are estimated using samples from a single trajectory generated by the underlying time-varying Markov processes.
A Two-Time-Scale Stochastic Optimization Framework with Applications in Control and Reinforcement Learning
In our two-time-scale approach, one scale is to estimate the true gradient from these samples, which is then used to update the estimate of the optimal solution.
Finite-Time Convergence Rates of Decentralized Stochastic Approximation with Applications in Multi-Agent and Multi-Task Learning
We study a decentralized variant of stochastic approximation, a data-driven approach for finding the root of an operator under noisy measurements.
A Decentralized Policy Gradient Approach to Multi-task Reinforcement Learning
We develop a mathematical framework for solving multi-task reinforcement learning (MTRL) problems based on a type of policy gradient method.
Fast Compressive Sensing Recovery Using Generative Models with Structured Latent Variables
Deep learning models have significantly improved the visual quality and accuracy on compressive sensing recovery.
