Combination therapy refers to the use of multiple treatments - such as surgery, medication, and behavioral therapy - to cure a single disease, and has become a cornerstone for treating various conditions including cancer, HIV, and depression. All possible combinations of treatments lead to a collection of treatment regimens (i.e., policies) with mixed scopes, or what physicians could observe and which actions they should take depending on the context. In this paper, we investigate the online reinforcement learning setting for optimizing the policy space with mixed scopes. In particular, we develop novel online algorithms that achieve sublinear regret compared to an optimal agent deployed in the environment. The regret bound has a dependency on the maximal cardinality of the induced state-action space associated with mixed scopes. We further introduce a canonical representation for an arbitrary subset of interventional distributions given a causal diagram, which leads to a non-trivial, minimal representation of the model parameters.

Y-axis: Cross Entropy Loss on validation set. Figure 1 shows the validation loss changes with respect to training time for 50k steps as supplementary results for the experiments in Section 5. In general, Skyformer converges faster and finishes 50k steps earlier than vanilla Attention and Kernelized Attention over all tasks. We further remark that on Text Classification, all models quickly fall into over-fitting, and thus the validation losses rise quickly. On Pathfinder, due to the difficulty of training, in the trial shown in the figure vanilla Attention fails to reach the best long-time limit under a certain setting. Figure 2 shows the singular value distribution of attention output from the second layer of a trained vanilla transformer.

We initiate the study of quantum algorithms for optimizing approximately convex functions. Given a convex set K Rn and a function F: Rn Rsuch that there exists a convex function f: K R satisfying supx K|F(x) f(x)| /n, our quantum algorithm finds an x K such that F(x) minx KF(x) using O(n3) quantum evaluation queries to F. This achieves a polynomial quantum speedup compared to the best-known classical algorithms. As an application, we give a quantum algorithm for zeroth-order stochastic convex bandits with O(n5 log2 T) regret, an exponential speedup in T compared to the classical Ω( T) lower bound. Technically, we achieve quantum speedup in nby exploiting a quantum framework of simulated annealing and adopting a quantum version of the hit-and-run walk. Our speedup in T for zeroth-order stochastic convex bandits is due to a quadratic quantum speedup in multiplicative error of mean estimation.

We propose and analyze a reinforcement learning principle that approximates the1 Bellman equations by enforcing their validity only along an user-defined space of2 test functions. Focusing on applications to model-free offline RL with function3 approximation, we exploit this principle to derive confidence intervals for off-policy4 evaluation, as well as to optimize over policies within a prescribed policy class.5 We prove an oracle inequality on our policy optimization procedure in terms of6 a trade-off between the value and uncertainty of an arbitrary comparator policy.7 Different choices of test function spaces allow us to tackle different problems8 within a common framework. We characterize the loss of efficiency in moving9 from on-policy to off-policy data using our procedures, and establish connections10 to concentrability coefficients studied in past work. We examine in depth the11 implementation of our methods with linear function approximation, and provide12 theoretical guarantees with polynomial-time implementations even when Bellman13 closure does not hold.14