arXiv Machine Learning August 10, 2026 By Neal Batra

From Optimal Actions to World Models: Identifiability of Transition Kernels in Discounted MDPs

Read the original on arXiv Machine Learning →

arXiv:2608. 07301v1 Announce Type: new Abstract: We study what can be recovered about the transition probabilities of a Markov decision process from optimal actions alone.

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.

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 Machine Learning

Jun 2

Online Learning in MDPs with Partially Adversarial Transitions and Losses

arXiv:2602. 09474v2 Announce Type: replace Abstract: We study reinforcement learning in MDPs whose transition function is stochastic at most steps but may behave adversarially at a fixed subset of $\Lambda$ steps per episode.

By Ofir Schlisselberg, Tal Lancewicki, Yishay Mansour

reinforcement-learning safety

arXiv Machine Learning

Aug 31

Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement Learning

The paper challenges the common assumption that the successor measure in reinforcement learning is approximately low-rank, showing instead that a low-rank structure emerges in a shifted successor measure that ignores initial transitions. It provides finite-sample guarantees for estimating this low-rank approximation, introduces Type II Poincaré inequalities to bound spectral recoverability, and links the necessary shift to the decay of high-order singular values and local mixing properties. Experiments confirm that shifting the successor measure improves goal-conditioned RL performance.

By Bastien Dubail, Stefan Stojanovic, Alexandre Prouti\`ere

reinforcement-learning

arXiv Machine Learning

Jul 24

Exploiting Exogenous Structure for Sample-Efficient Reinforcement Learning

arXiv:2409. 14557v4 Announce Type: replace-cross Abstract: We study a structured class of Markov Decision Processes, known as Exo-MDPs, in which the state space is partitioned into exogenous and endogenous components.

By Jia Wan, Sean R. Sinclair, Devavrat Shah, Martin J. Wainwright

agents reinforcement-learning

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

Aug 14

Decentralized Multi-Player Q-Learning in Episodic Markov Decision Processes with Information Asymmetry

arXiv:2608. 12753v1 Announce Type: new Abstract: We study decentralized multi-player reinforcement learning in episodic tabular Markov decision processes (MDPs) under three forms of information asymmetry: (A) unobserved actions with common rewards, (B) observed actions with independent rewards, and (C) unobserved actions with independent rewards.

By Larissa Xu, King Bi, William Chang

agents reinforcement-learning benchmarks

One email a morning, machine-written

Related stories

Optimal Multi-Reward Reinforcement Learning

Online Learning in MDPs with Partially Adversarial Transitions and Losses

Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement Learning

Exploiting Exogenous Structure for Sample-Efficient Reinforcement Learning

Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence

Decentralized Multi-Player Q-Learning in Episodic Markov Decision Processes with Information Asymmetry