1 code implementation • 26 Oct 2022 • Thomas Kleine Buening, Victor Villin, Christos Dimitrakakis
Even with abundant data, current inverse reinforcement learning methods that focus on learning from a single environment can fail to handle slight changes in the environment dynamics.
no code implementations • 15 Oct 2021 • Victor Villin, Naoki Masuyama, Yusuke Nojima
To that effect, this paper considers an existing evolutionary reinforcement learning framework which exploits multi-objective optimization as a way to obtain policies that succeed at behavior-related tasks as well as completing the main goal.