arXiv Machine Learning August 10, 2026 By Pahan Dewasurendra

Multiscale Reward Hedging from Correct Demonstrations

Read the original on arXiv Machine Learning →

arXiv:2608. 06825v1 Announce Type: new 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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Sep 24

Tight Regret Bound for Online Inverse Linear Optimization via Multiscale Matrix Weights

arXiv:2609. 26978v1 Announce Type: cross Abstract: We study online inverse linear optimization with a fixed unknown linear utility: in each round, an environment presents a compact action set, the learner recommends an action from it, and the environment returns an action that maximizes the utility over the same set.

By Shinsaku Sakaue

arXiv Statistics ML

3d ago

Tighter Regret Bounds for Contextual Action-Set Reinforcement Learning

arXiv:2605.15692v2 Announce Type: replace-cross Abstract: We study episodic reinforcement learning with fixed reward and transition functions, but with episode-dependent admissible action sets that a...

By Zijun Chen, Zihan Zhang

reinforcement-learning safety

arXiv Machine Learning

Jul 23

Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence

arXiv:2607. 19854v1 Announce Type: new Abstract: We study horizon-free regret minimization for finite-horizon time-homogeneous tabular Markov decision processes with $S$ states, $A$ actions, horizon $H$, and per-trajectory total reward bounded by $1$.

By Runlong Zhou, Zihan Zhang, Maryam Fazel, Simon S. Du

reinforcement-learning

arXiv Machine Learning

4d ago

Optimal Multi-Reward Reinforcement Learning

arXiv:2609.36486v1 Announce Type: new Abstract: We study an unknown-transition finite-horizon Markov decision process (MDP) with a finite collection of known reward functions $\{r^1, r^2, \ldots, r^M...

By Zijun Chen, Zihan Zhang

reinforcement-learning

arXiv Statistics ML

3d ago

Lower Bounds for Linear-Oracle Online Learning

arXiv:2609.38375v1 Announce Type: new Abstract: Can a constant number of linear minimizations per round improve on the $T^{3/4}$ regret rate of online Frank-Wolfe on general convex sets? Weibel et al...

By Mohit Sinha

arXiv Machine Learning

1d ago

Geometry-Dependent Bounds for Online Non-Monotone DR-Submodular Maximization

arXiv:2610. 00545v1 Announce Type: new Abstract: We study adversarial online maximization of nonnegative, non-monotone DR-submodular functions over compact convex down-closed sets.

By Vaneet Aggarwal

benchmarks safety

One email a morning, machine-written

Related stories

Tight Regret Bound for Online Inverse Linear Optimization via Multiscale Matrix Weights

Tighter Regret Bounds for Contextual Action-Set Reinforcement Learning

Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence

Optimal Multi-Reward Reinforcement Learning

Lower Bounds for Linear-Oracle Online Learning

Geometry-Dependent Bounds for Online Non-Monotone DR-Submodular Maximization