most citedRandomized Exploration for Reinforcement Learning with General Value Function Approximation

3 citations · 7 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG2021

Settling the Horizon-Dependence of Sample Complexity in Reinforcement Learning

Yuanzhi Li, Ruosong Wang, Lin F. Yang

Recently there is a surge of interest in understanding the horizon-dependence of the sample complexity in reinforcement learning (RL). Notably, for an RL environment with horizon l…

cs.LG2021

Breaking the Moments Condition Barrier: No-Regret Algorithm for Bandits with Super Heavy-Tailed Payoffs

Han Zhong, Jiayi Huang, Lin F. Yang +1

Despite a large amount of effort in dealing with heavy-tailed error in machine learning, little is known when moments of the error can become non-existential: the random noise

cs.LG2021

Theoretically Principled Deep RL Acceleration via Nearest Neighbor Function Approximation

Junhong Shen, Lin F. Yang

Recently, deep reinforcement learning (RL) has achieved remarkable empirical success by integrating deep neural networks into RL frameworks. However, these algorithms often require…

cs.LG20212 cited

Safe Reinforcement Learning with Linear Function Approximation

Sanae Amani, Christos Thrampoulidis, Lin F. Yang

Safety in reinforcement learning has become increasingly important in recent years. Yet, existing solutions either fail to strictly avoid choosing unsafe actions, which may lead to…

cs.LG20213 cited

Randomized Exploration for Reinforcement Learning with General Value Function Approximation

Haque Ishfaq, Qiwen Cui, Viet Nguyen +5

We propose a model-free reinforcement learning algorithm inspired by the popular randomized least squares value iteration (RLSVI) algorithm as well as the optimism principle. Unlik…

cs.LG20212 cited

Provably Correct Optimization and Exploration with Non-linear Policies

Fei Feng, Wotao Yin, Alekh Agarwal +1

Policy optimization methods remain a powerful workhorse in empirical Reinforcement Learning (RL), with a focus on neural policies that can easily reason over complex and continuous…