1 code implementation • 6 Oct 2020 • Yuji Kanagawa, Tomoyuki Kaneko
We consider the problem of autonomously learning reusable temporally extended actions, or options, in reinforcement learning.
2 code implementations • 17 Apr 2019 • Yuji Kanagawa, Tomoyuki Kaneko
Following these studies, we propose the use of roguelikes as a benchmark for evaluating the generalization ability of RL agents.