Education
Best-of-All-Worlds Bounds for Online Learning with Feedback Graphs
We study the online learning with feedback graphs framework introduced by Man-nor and Shamir [24], in which the feedback received by the online learner is specified by a graphnull over the available actions.
Continual World: A Robotic Benchmark For Continual Reinforcement Learning
Evaluation of CL methods is challenging.
Supplementary Material T able of Contents
A Laplace behavioral reference policy may be able to mitigate some of the problems posed by Proposition 1 due to the heavy tails of the distribution. Tikhonov regularization does not resolve the issue with calibration of uncertainties. A W AC performs online fine-tuning of a policy pre-trained on offline. BRAC regularizes the online policy against an offline behavioral policy as our method does. DAPG incorporates offline data into policy gradients by initially pre-training with a behaviorally cloned policy and then augmenting the RL loss with a supervised-learning loss.
Appendix A Training
We follow the same setup as in Rae et al.
Adapting to Online Label Shift with Provable Guarantees Yong Bai
The non-stationarity nature and the lack of supervision make the problem challenging to be tackled.
