BriefGPT.xyz
Apr, 2018
Gotta Learn Fast: 强化学习泛化新基准
Gotta Learn Fast: A New Benchmark for Generalization in RL
HTML
PDF
Alex Nichol, Vicki Pfau, Christopher Hesse, Oleg Klimov, John Schulman
TL;DR
该研究介绍了一种基于Sonic the Hedgehog的强化学习基准测试，旨在测试迁移学习和小样本学习算法在强化学习领域的性能，并在该基准测试上提出并评估了一些基准算法。
Abstract
In this report, we present a new
reinforcement learning
(RL)
benchmark
based on the
sonic the hedgehog
(TM) video game franchise. This
→