Regrets_Bounds_of_Concurrent_Thompson_Sampling

Do the main claims made in the abstract and introduction accurately reflect the paper's 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)? [Y es] (b) Did you specify all the training details (e.g., data splits, hyperparameters, how they Did you report error bars (e.g., with respect to the random seed after running experiments multiple times)? 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? [Y es] 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) As a matter of fact, in our simulation, we set reward functions under both settings drawn from random normal distribution. Let the parameters in Algorithm 5 take the following values: = r nTS A + 12!S And the rest of the proof follows similarly as in [3] Lemma 5.3. The proof follows in the same way as in Lemma 5.4 of [3]. With (F.1) we have: Tn SA (2 Lemma B.5. (Diameter of the extended MDP).