4 citations · 7 across the 7 of their papers we have counts for
8 papers · 1 filter
Thompson Sampling for Unimodal Bandits
Long Yang, Zhao Li, Zehong Hu +4
In this paper, we propose a Thompson Sampling algorithm for \emph{unimodal} bandits, where the expected reward is unimodal over the partially ordered arms. To exploit the unimodal…
On Convergence of Gradient Expected Sarsa()
Long Yang, Gang Zheng, Yu Zhang +3
We study the convergence of with linear function approximation. We show that applying the off-line estimate (multi-step bootstrapping) to $\mathtt{Expe…
Sample Complexity of Policy Gradient Finding Second-Order Stationary Points
Long Yang, Qian Zheng, Gang Pan
The goal of policy-based reinforcement learning (RL) is to search the maximal point of its objective. However, due to the inherent non-concavity of its objective, convergence to a…
Gradient Q: A Unified Algorithm with Function Approximation for Reinforcement Learning
Long Yang, Yu Zhang, Qian Zheng +2
Full-sampling (e.g., Q-learning) and pure-expectation (e.g., Expected Sarsa) algorithms are efficient and frequently used techniques in reinforcement learning. Q is the firs…
FiDi-RL: Incorporating Deep Reinforcement Learning with Finite-Difference Policy Search for Efficient Learning of Continuous Control
Longxiang Shi, Shijian Li, Longbing Cao +3
In recent years significant progress has been made in dealing with challenging problems using reinforcement learning.Despite its great success, reinforcement learning still faces c…
TBQ(): Improving Efficiency of Trace Utilization for Off-Policy Reinforcement Learning
Longxiang Shi, Shijian Li, Longbing Cao +2
Off-policy reinforcement learning with eligibility traces is challenging because of the discrepancy between target policy and behavior policy. One common approach is to measure the…