This paper studies the problem of safe meta-reinforcement learning (safe metaRL), where an agent efficiently adapts to unseen tasks while satisfying safety constraints at all times during adaptation. We propose a framework consisting of two complementary modules: safe policy adaptation and safe meta-policy training. The first module introduces a novel one-step safe policy adaptation method that admits a closed-form solution, ensuring monotonic improvement, constraint satisfaction at every step, and high computational efficiency. The second module develops a Hessian-free meta-training algorithm that incorporates safety constraints on the meta-policy and leverages the analytical form of the adapted policy to enable scalable optimization. Together, these modules yield three key advantages over existing safe meta-RL methods: (i) superior optimality, (ii) anytime safety guarantee, and (iii) high computational efficiency. Beyond existing safe meta-RL analyses, we prove the anytime safety guarantee of policy adaptation and provide a lower bound of the expected total reward of the adapted policies compared with the optimal policies, which shows that the adapted policies are nearly optimal. Empirically, our algorithm achieves superior optimality, strict safety compliance, and substantial computational gains--up to 70% faster training and 50% faster testing--across diverse locomotion and navigation benchmarks.

We investigate refinements of the mean-payoff criterion in two-player zero-sum perfect-information stochastic games. A strategy is Blackwell optimal if it is optimal in the discounted game for all discount factors sufficiently close to 1.

We study online convex optimisation on ℓp-balls in Rd for p > 2. While always sub-linear, the optimal regret exhibits a shift between the high-dimensional setting (d > T), when the dimension d is greater than the time horizon T and the low-dimensional setting (d T). We show that Follow-the-Regularised-Leader (FTRL) with time-varying regularisation which is adaptive to the dimension regime is anytime optimal for all dimension regimes. Motivated by this, we ask whether it is possible to obtain anytime optimality of FTRL with fixed non-adaptive regularisation. Our main result establishes that for separable regularisers, adaptivity in the regulariser is necessary, and that any fixed regulariser will be sub-optimal in one of the two dimension regimes. Finally, we provide lower bounds which rule out sublinear regret bounds for the linear bandit problem in sufficiently high-dimension for all ℓp-balls with p 1.

We study the problem of computing an optimal large language model (LLM) policy for the constrained alignment problem, where the goal is to maximize a primary reward objective while satisfying constraints on secondary utilities. Despite the popularity of Lagrangian-based LLM policy search in constrained alignment, iterative primal-dual methods often fail to converge, and non-iterative dual-based methods do not achieve optimality in the LLM parameter space. To address these challenges, we employ Lagrangian duality to develop an iterative dual-based alignment method that alternates between updating the LLM policy via Lagrangian maximization and updating the dual variable via dual descent. In theory, we characterize the primal-dual gap between the primal value in the distribution space and the dual value in the LLM parameter space. We further quantify the optimality gap of the learned LLM policies at near-optimal dual variables with respect to both the objective and the constraint functions. These results prove that dual-based alignment methods can find an optimal constrained LLM policy, up to an LLM parametrization gap. We demonstrate the effectiveness and merits of our approach through extensive experiments conducted on the PKU-SafeRLHF and Anthropic HH-RLHF datasets.

It has been recently shown that e-processes are sufficient for sequential testing in the following sense: every level-$α$ sequential test can be obtained by thresholding an e-process at $1/α$. However, in the above result, neither does the test have to be asymptotically optimal (in terms of stopping times) nor does the e-process have to be asymptotically log-optimal. It has separately been shown that asymptotically log-optimal e-processes yield asymptotically optimal sequential tests. In this paper, we prove the converse, arguably completing the story: it is possible to aggregate asymptotically optimal sequential tests into asymptotically log-optimal e-processes. This is accomplished by using a new class of WAIT e-processes: those that are Weighted Aggregates of Indicators of stopping Times that begin at zero, are nondecreasing and increase to infinity under the alternative at the optimal rate. Importantly, the paper discusses several nuances in the varied definitions of asymptotic (log-)optimality.

We thank the reviewers for their insightful feedback, and we appreciate the opportunity to improve our paper. We will1 address typos and notational inconsistencies in the updated version.2 Response to Reviewer 1:3 We would like to emphasize that Theorem 1 is the most important contribution of our paper due to its generality.4 By considering the set of all possible classifiers, it provides lower bounds on adversarial robustness for any pair of5 class-conditional distributions. As we show in our experimental results in Section 6, we are able to obtain lower bounds6 for arbitrary real-world datasets by constructing the empirical distribution for these. In our estimation, these results7 serve to provide theoretical validation for adversarial training for low perturbation budgets as well as to highlight the8 gap to optimality for higher budgets.9

Mean estimation under differential privacy is a fundamental problem, but worstcase optimal mechanisms do not offer meaningful utility guarantees in practice when the global sensitivity is very large. Instead, various heuristics have been proposed to reduce the error on real-world data that do not resemble the worst-case instance. This paper takes a principled approach, yielding a mechanism that is instance-optimal in a strong sense. In addition to its theoretical optimality, the mechanism is also simple and practical, and adapts to a variety of data characteristics without the need of parameter tuning. It easily extends to the local and shuffle model as well.

Deterministic RLDeterministic system is often the starting case in the study of sample-efficient algorithms, where the issue of exploration and exploitation trade-off is more clearly revealed since both the transition kernel and reward function are deterministic. The seminal work [81] proposes a sample-efficient algorithm for Q-learning that works for a family of function classes. Recently, [21] studies the agnostic setting where the optimal Q-function can only be approximated by a function class with approximation error. The algorithm in [21] learns the optimal policy with the number of trajectories linear with the eluder dimension. Consider MDPM where the transition is deterministic. Assume the function class in Definition 3.1 satisfies Assumption 2.1 and Assumption 2.2. For any t (0,1), if d Ω(log(BW/λ))and n d poly(κ,k,λ,BW,Bϕ,H,log(d/t)), then with probability at least 1 tAlgorithm 1 returns the optimal policy π .