K. Young

发表

Doubly-Asynchronous Value Iteration: Making Value Iteration Asynchronous in Actions

R. Sutton, Tian Tian, K. Young, 2022, ArXiv.

The Benefits of Model-Based Generalization in Reinforcement Learning

J. Schmidhuber, A. Ramesh, Louis Kirsch, 2022, ArXiv.

MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments

Tian Tian, Kenny Young, Tian Tian, 2019 .

Metatrace: Online Step-size Tuning by Meta-gradient Descent for Reinforcement Learning Control pdf

Matthew E. Taylor, Kenny Young, Baoxiang Wang, 2018, ArXiv.

Metatrace Actor-Critic: Online Step-Size Tuning by Meta-gradient Descent for Reinforcement Learning Control

Matthew E. Taylor, Kenny Young, Baoxiang Wang, 2018, IJCAI.

MinAtar: An Atari-inspired Testbed for More Efficient Reinforcement Learning Experiments pdf

Tian Tian, Kenny Young, Tian Tian, 2019, ArXiv.

Neurohex: A Deep Q-learning Hex Agent

Kenny Young, Gautham Vasan, Ryan Hayward, 2016, CGW@IJCAI.

Directly Estimating the Variance of the λ-Return Using Temporal-Difference Methods pdf

Martha White, Richard S. Sutton, Adam White, 2018, ArXiv.

Variance Reduced Advantage Estimation with δ Hindsight Credit Assignment

K. Young, 2019, ArXiv.

The Benefits of Model-Based Generalization in Reinforcement Learning

J. Schmidhuber, A. Ramesh, Louis Kirsch, 2022, ICML.