Policy Regret
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Minimax-Optimal Policy Regret in Partially Observable Markov Games
arXiv:2606.02363v1 Announce Type: new Abstract: We study sequential decision-making in partially observable environments against strategic, adaptive opponents, modeled as partially observable Markov games (POMGs). The central challenge is to learn latent dynamics from partial observations while facing an adversary whose behavior depends on the learner's strategy, making standard regret notions inadequate. We prove that an epoch-based optimistic maximum-likelihood algorithm achieves...
Regret Minimization with Adaptive Opponents in Repeated Games
arXiv:2606.06486v1 Announce Type: new Abstract: In this paper, we study regret minimization in repeated games with \emph{adaptive} opponents who can respond based on histories of play. The standard metric of \emph{external regret} in online learning is known to fail to capture such adaptivity. To account for players' counterfactual reasoning, we introduce {\tt Repeated Policy Regret (RP-Regret)}, a game-theoretic metric that measures the difference between the \emph{realized} and the...
Evaluating AI Investment Strategies
arXiv:2606.08791v1 Announce Type: cross Abstract: We study the problem of auditing a black-box algorithmic decision-maker from observable inputs and outputs alone. Our main result is an exact decomposition: under precisely characterized conditions, the cumulative \emph{regret} of a dynamic policy equals the sum of per-period covariances between the cost vector and the policy's decision. This extends the single-period identity of Aldridge~(2026) to the full multi-period setting of stochastic...
Efficient Exploration for Iterative Nash Preference Optimization
arXiv:2606.01382v1 Announce Type: new Abstract: Preference alignment is central to improving large language models, but standard reward-based formulations can be restrictive when human preferences are cyclic, non-transitive, or otherwise not representable by a scalar reward. Nash Learning from Human Feedback (NLHF) addresses this limitation by modeling alignment as a preference game and targeting a Nash equilibrium rather than a reward maximizer. However, the learning-theoretic foundations...
Annealed Softmax Greedy in Many-Armed Bayesian Bandits
Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) and group-based policy optimization methods such as GRPO update a stochastic policy by sampling multiple completions per prompt and increasing the policy's probability on those with higher reward, regularized by a KL penalty toward a reference policy. These updates do not include explicit mechanisms that track epistemic uncertainty. This paper studies a stylized explanation for why such uncertainty-agnostic...
Workload-Aware Autotuning of Block Size in Square-Root Decomposition
arXiv:2606.06145v1 Announce Type: new Abstract: The textbook choice B=sqrt(n) for square-root decomposition is asymptotically natural, but it is not always the fastest implementation choice. We study block-size autotuning as a reproducible algorithm-engineering problem and show that a learned workload model can improve over fixed sqrt(n) on the tested implementation. Under repeated grouped cross-validation, the best policy is a full-feature KNN-9 model that reduces mean regret from 1.2882 to...
Learn to Match: Two-Sided Matching with Temporally Extended Feedback
Announce Type: new Abstract: Two-sided matching markets often involve information that unfolds over time through interviews, repeated interaction, learning, and separation. Existing matching models typically reduce this process to immediate sub-Gaussian feedback about fixed preferences, missing settings where payoff-relevant information is revealed gradually and changes future matching decisions. We introduce a framework with temporally extended feedback, that formulates two-sided matching...
Reinforcement Learning from Rich Feedback with Distributional DAgger
Announce Type: new Abstract: Reasoning models have advanced rapidly, but the dominant reinforcement learning from verifiable rewards (RLVR) recipe remains surprisingly narrow: sample many responses and reward each with a single bit indicating whether the final answer is correct. Yet many settings provide rich feedback, including execution traces, tool outputs, expert corrections, and model self-evaluations. We study how to use such feedback through a distributional variant of the classic...
Reinforcement Learning from Rich Feedback with Distributional DAgger
arXiv:2606.05152v2 Announce Type: replace Abstract: Reasoning models have advanced rapidly, but the dominant reinforcement learning from verifiable rewards (RLVR) recipe remains surprisingly narrow: sample many responses and reward each with a single bit indicating whether the final answer is correct. Yet many settings provide rich feedback, including execution traces, tool outputs, expert corrections, and model self-evaluations. We study how to use such feedback through a distributional...
Online KL-Regularized Reinforcement Learning with Function Approximation under Misspecification
arXiv:2606.06053v1 Announce Type: new Abstract: We study KL-regularized contextual bandits and episodic reinforcement learning (RL) under general function approximation with model misspecification. Existing guarantees rely on realizability and therefore do not extend to misspecified models, where classical regret bounds may fail. This work introduces KL misspecification formulations for contextual bandits and episodic RL and analyzes regression-based algorithms with Gibbs policy updates.