5 citations · 26 across the 23 of their papers we have counts for
10 papers · 1 filter
Solving Multi-Arm Bandit Using a Few Bits of Communication
Osama A. Hanna, Lin F. Yang, Christina Fragouli
The multi-armed bandit (MAB) problem is an active learning framework that aims to select the best among a set of actions by sequentially observing rewards. Recently, it has become…
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…
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 …
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…
On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning
Weichao Mao, Lin F. Yang, Kaiqing Zhang +1
Multi-agent reinforcement learning (MARL) algorithms often suffer from an exponential sample complexity dependence on the number of agents, a phenomenon known as \emph{the curse of…
Near-Optimal Reward-Free Exploration for Linear Mixture MDPs with Plug-in Solver
Xiaoyu Chen, Jiachen Hu, Lin F. Yang +1
Although model-based reinforcement learning (RL) approaches are considered more sample efficient, existing algorithms are usually relying on sophisticated planning algorithm to cou…
Gap-Dependent Unsupervised Exploration for Reinforcement Learning
Jingfeng Wu, Vladimir Braverman, Lin F. Yang
For the problem of task-agnostic reinforcement learning (RL), an agent first collects samples from an unknown environment without the supervision of reward signals, then is reveale…
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…
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…
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…