Langevin dqn

V Dwaracherla, B Van Roy - arXiv preprint arXiv:2002.07282, 2020 - arxiv.org
Algorithms that tackle deep exploration--an important challenge in reinforcement learning--
have relied on epistemic uncertainty representation through ensembles or other …

Parameterized indexed value function for efficient exploration in reinforcement learning

T Tan, Z Xiong, VR Dwaracherla - … of the AAAI Conference on Artificial …, 2020 - ojs.aaai.org
It is well known that quantifying uncertainty in the action-value estimates is crucial for
efficient exploration in reinforcement learning. Ensemble sampling offers a relatively …

[图书][B] Data-Driven Adaptive Traffic Signal Control via Deep Reinforcement Learning

T Tan - 2020 - search.proquest.com
Adaptive traffic signal control (ATSC) system serves a significant role for relieving urban
traffic congestion. The system is capable of adjusting signal phases and timings of all traffic …

[图书][B] Posterior Sampling for Efficient Reinforcement Learning

VR Dwaracherla - 2021 - search.proquest.com
Reinforcement learning has shown tremendous success over the past few years. Much of
this recent success can be attributed to agents learning from an inordinate amount of data in …