In risk-averse reinforcement learning (RL), the goal is to optimize some risk measure of the returns.

Do the main claims made in the abstract and introduction accurately reflect the paper's Did you discuss any potential negative societal impacts of your work? Did you include complete proofs of all theoretical results? If you ran experiments... (a) Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [N/A] (b) Did you specify all the training details (e.g., data splits, hyperparameters, how they Did you include the total amount of compute and the type of resources used (e.g., type Did you include any new assets either in the supplemental material or as a URL?[N/A] Did you discuss whether and how consent was obtained from people whose data you're If you used crowdsourcing or conducted research with human subjects... (a) In this section, we prove Theorems 6 and 12 which give upper bounds on the sample complexity in the standard and agnostic settings respectively. The following is a well-known result that relates covering numbers to the pseudo dimension (cf. A.1 The Standard Model: Proof of Theorem 6 First, we relate covering numbers to this error measure.

A recent trend in online algorithms has seen the use of future predictions generated by ML techniques to bypass pessimistic worst-case lower bounds.

This induces to the use of Laplacian regularization.

In this work, we show for the first time that error compensated gradient compression methods can be accelerated. In particular, we propose and study the error compensated loopless Katyusha method, and establish an accelerated linear convergence rate under standard assumptions.