Christian Steinparz, Thomas Schmied, Fabian Paischer, Marius-Constantin Dinu, Vihang Patil, Angela Bitto-Nemling, Hamid Eghbal-zadeh, and Sepp Hochreiter

In lifelong learning, an agent learns throughout its entire life without resets, in a constantly changing environment, as we humans do. Consequently, lifelong learning comes with a plethora of research problems such as continual domain shifts, which result in non-stationary rewards and environment dynamics. These non-stationarities are difficult to detect and cope with due to their continuous nature. Therefore, exploration strategies and learning methods are required that are capable of tracking the steady domain shifts, and adapting to them. We propose Reactive Exploration to track and react to continual domain shifts in lifelong reinforcement learning, and to update the policy correspondingly. To this end, we conduct experiments in order to investigate different exploration strategies. We empirically show that representatives of the policy-gradient family are better suited for lifelong learning, as they adapt more quickly to distribution shifts than Q-learning. Thereby, policy-gradient methods profit the most from Reactive Exploration and show good results in lifelong learning with continual domain shifts. Our code is available on GitHub.

arXiv:2207.05742, 2022-07-12.

Download
View paper
IARAI Authors
Dr Angela Bitto-Nemling, Dr Sepp Hochreiter
Research
Reinforcement Learning
Keywords
Domain Shift, Lifelong Learning, Reinforcement Learning

©2022 IARAI - INSTITUTE OF ADVANCED RESEARCH IN ARTIFICIAL INTELLIGENCE

Imprint | Privacy Policy

Stay in the know with developments at IARAI

We can let you know if there’s any

updates from the Institute.
You can later also tailor your news feed to specific research areas or keywords (Privacy)
Loading

Log in with your credentials

Forgot your details?

Create Account