cs.LGAug 7, 2026

Multiscale Reward Hedging from Correct Demonstrations

Authors: Pahan Dewasurendra

Organizations: Johns Hopkins University

Abstract

Learning from correct demonstrations is harder than supervised learning when many answers are correct: after predicting, the learner sees one valid answer but not whether its own answer was valid, nor any reward. Existing reward-hedging guarantees consequently assume a finite reward class. We give the first horizon-free guarantee for continuous classes. The key is to hedge in one shared vote over tolerant optimality tests at every accuracy scale. A target reward has one surviving proxy per scale, and a prediction with gap above that scale doubles the proxy. This yields the simultaneous tail bound {t:t>2j}log2N(G,2j1)+j|\{t:\ell_t>2^{-j}\}|\leq \log_2\mathcal N(\mathcal G,2^{-j-1})+j, where G\mathcal G is the class of optimality-gap functions. Integrating the tails gives cumulative hidden gap bounded by a metric-entropy integral, independently of the number of rounds. Polynomial entropy (A/ε)d(A/ε)^d gives O(dlogA)O(d\log A) total gap and a fast O(d/m)O(d/m) statistical rate. For bounded linear contextual recommendation, the result is O(d)O(d) regret for arbitrary compact menus. This is the first polynomial finite bound without structural restrictions on the menus, at the price of improper prediction. Although the general vote can be expensive, it is exactly polynomial-time for one-dimensional Lipschitz parameter curves. Fixed-radius rank-two recommendation takes O(KT2)O(KT^2) time for menus of size KK. We also prove an Ω(d)Ω(d) lower bound, low-rank and bounded ReLU-network corollaries, and a robust theorem that adds only the demonstrator's cumulative suboptimality. A reproducible adaptive stress test illustrates the predicted scale adaptation. After factorization, an exact MovieLens audit runs in 1.7 CPU seconds across ten users and improves mean latent gap over both a demonstrated-rating policy and a proper online baseline. The learner uses only action demonstrations and never observes a reward or a loss.

Explore similar work

Sep 14, 2026cs.LG

Bandits with Probing: Optimal Regret and the Limits of Winner Feedback

A learner probes at most kk of nn arms each round, receives the maximum of their rewards in [0,1][0,1], and competes with the best fixed arm. When does the probing advantage pay for learning? We determine two minimax laws. Under independent stochastic rewards with winner feedback (the maximum and a winning label), or on arbitrary fixed sequences given a single signed contrast between block maxima, the minimax regret has order Φn,k(T)=min{nknT,nkk}Φ_{n,k}(T)=\min\{\frac{n-k}{n}T,\frac{n-k}{k}\}, 2k<n2\le k<n. Under winner feedback, both arbitrary joint i.i.d. rewards and fixed sequences have minimax regret of order Rn,k(T)=nknmin{T,n+Tk,nTk}R_{n,k}(T)=\frac{n-k}{n}\min\{T,\frac{n+T}{k},\sqrt{\frac{nT}{k}}\}. Both laws have universal constants and anytime upper bounds. The first reduces regret to a pure coverage cost: same-round contrasts absorb the stability cost, and independence permits exact resampling whose gains fund sample advancement. The second adds a learning cost that becomes comparable to coverage at horizon nn; beyond nknk, numerical maxima improve over labels alone. The lower bound allows every adaptive action size.
Yongjie Guan
May 29, 2026cs.LG

Inverse Reinforcement Learning without an Optimal Demonstrator: A Feasible Reward Set Approach

Inverse reinforcement learning (IRL) typically assumes demonstrations from a single optimal demonstrator, but in many applications data come from multiple imperfect demonstrators with heterogeneous suboptimality levels. We study reward learning in this setting through a feasible-reward-set framework: for each demonstrator, we encode its declared suboptimality level as a linear constraint and intersect the resulting feasible sets across demonstrators. Our theoretical analysis shows that the joint feasible set shrinks monotonically as data are added, and we give an exact characterization of when a new demonstrator strictly tightens it. We further establish two recovery guarantees for the feasible reward set of the ground-truth optimal demonstrator: one bound depends on closeness to the optimal occupancy, while the other requires only sufficient coverage and no near-optimal demonstrator. On the practical side, we introduce strategies to address the inherent reward ambiguity in the obtained reward set and provide an offline algorithm with function approximation for high-dimensional environments. Experiments in tabular grid-world and large language model (LLM) fine-tuning settings are consistent with the theoretical predictions and demonstrate the effectiveness of the proposed framework over baselines.
Kihyun Kim, Shripad Deshmukh, Nikos Vlassis +1
Sep 14, 2026cs.LG

Nearly Minimax-Optimal Regret for Linear Contextual Bandits with Arbitrary Adaptive Action Sets

We study stochastic linear contextual bandits with arbitrary action menus that may depend on the fixed parameter and the interaction history. We establish matching upper and lower bounds, up to logarithmic factors. Let dd be the dimension, KK be the menu size, and TT the time horizon. For 2Kd2\le K\le d, we prove an upper bound O~(K1/4dT)\widetilde O(K^{1/4}\sqrt{dT}). When Td2T\ge d^2, we further prove a lower bound Ω(K1/4dT)Ω(K^{1/4}\sqrt{dT}). Thus, for Td2T\ge d^2 and 2Kd2\le K\le d, the upper and lower bounds match up to logarithmic factors, and the polynomial dependence on KK is optimal. Compared with the previous O~(dKT)\widetilde O(\sqrt{dKT}) bound, our upper bound improves the dependence on KK by a factor of K1/4K^{1/4}. For KdK\ge d, we prove an upper bound O~d,T(dTmin{d,(dlogK)1/4})\widetilde O_{d,T}\left(\sqrt{dT}\min\{\sqrt d,(d\log K)^{1/4}\}\right) and a lower bound Ω(dTmin{d,(dlogKlog(2d))1/4})Ω\left(\sqrt{dT}\min\left\{\sqrt d,\left(\frac{d\log K}{\log(2d)}\right)^{1/4}\right\}\right). Here, O~d,T\widetilde O_{d,T} omits logarithmic factors only in dd and TT. In particular, for polynomially large KdK\ge d, the upper and lower bounds both scale as d3/4Td^{3/4}\sqrt T up to logarithmic factors, improving the standard O~(dT)\widetilde O(d\sqrt T) rate by a factor of d1/4d^{1/4}. As KK grows further, the regret smoothly recovers the dTd\sqrt T scale once logK\log K reaches order dd.
Tianyuan Jin