Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Mengdi Wang

Mengdi Wang

Deep Primal-Dual Reinforcement Learning: Accelerating Actor-Critic using Bellman Duality

Dec 07, 2017
Woon Sang Cho, Mengdi Wang

Figure 1 for Deep Primal-Dual Reinforcement Learning: Accelerating Actor-Critic using Bellman Duality

Access Paper or Ask Questions

Primal-Dual $π$ Learning: Sample Complexity and Sublinear Run Time for Ergodic Markov Decision Problems

Oct 17, 2017
Mengdi Wang

Figure 1 for Primal-Dual $π$ Learning: Sample Complexity and Sublinear Run Time for Ergodic Markov Decision Problems

Access Paper or Ask Questions

Near-Optimal Stochastic Approximation for Online Principal Component Estimation

Oct 05, 2017
Chris Junchi Li, Mengdi Wang, Han Liu, Tong Zhang

Figure 1 for Near-Optimal Stochastic Approximation for Online Principal Component Estimation

* Finalized version (bib and typos updated). To appear in Mathematical Programming

Access Paper or Ask Questions

Lower Bound On the Computational Complexity of Discounted Markov Decision Problems

May 20, 2017
Yichen Chen, Mengdi Wang

Figure 1 for Lower Bound On the Computational Complexity of Discounted Markov Decision Problems

Figure 2 for Lower Bound On the Computational Complexity of Discounted Markov Decision Problems

Figure 3 for Lower Bound On the Computational Complexity of Discounted Markov Decision Problems

Access Paper or Ask Questions

Stochastic Primal-Dual Methods and Sample Complexity of Reinforcement Learning

Dec 08, 2016
Yichen Chen, Mengdi Wang

Access Paper or Ask Questions

Accelerating Stochastic Composition Optimization

Jul 25, 2016
Mengdi Wang, Ji Liu, Ethan X. Fang

Figure 1 for Accelerating Stochastic Composition Optimization

Figure 2 for Accelerating Stochastic Composition Optimization

Figure 3 for Accelerating Stochastic Composition Optimization

Access Paper or Ask Questions