activity
20122020
most citedFinite-Sample Analysis of Proximal Gradient TD Algorithms

101 citations · 146 across the 4 of their papers we have counts for

collaborators

5 papers

cs.LG2020101 cited

Finite-Sample Analysis of Proximal Gradient TD Algorithms

Bo Liu, Ji Liu, Mohammad Ghavamzadeh +2

In this paper, we analyze the convergence rate of the gradient temporal difference learning (GTD) family of algorithms. Previous analyses of this class of algorithms use ODE techni…

cs.LG202019 cited

Regularized Off-Policy TD-Learning

Bo Liu, Sridhar Mahadevan, Ji Liu

We present a novel regularized off-policy convergent TD-learning method (termed RO-TD), which is able to learn sparse representations of value functions with low computationa…

cs.LG20205 cited

Proximal Gradient Temporal Difference Learning: Stable Reinforcement Learning with Polynomial Sample Complexity

Bo Liu, Ian Gemp, Mohammad Ghavamzadeh +3

In this paper, we introduce proximal gradient temporal difference learning, which provides a principled way of designing and analyzing true stochastic gradient temporal difference…

cs.LG2018

Dantzig Selector with an Approximately Optimal Denoising Matrix and its Application to Reinforcement Learning

Bo Liu, Luwan Zhang, Ji Liu

Dantzig Selector (DS) is widely used in compressed sensing and sparse learning for feature selection and sparse signal recovery. Since the DS formulation is essentially a linear pr…

cs.LG201221 cited

Sparse Q-learning with Mirror Descent

Sridhar Mahadevan, Bo Liu

This paper explores a new framework for reinforcement learning based on online convex optimization, in particular mirror descent and related algorithms. Mirror descent can be viewe…