arXiv AI June 30, 2026 By Ryohei Oura, Georgios Fainekos, Hideki Okamoto, Bardh Hoxha

Sample-Efficient Learning of Probabilistic Causes for Reachability in Markov Decision Processes with Probabilistic Guarantees

arXiv:2606. 29681v1 Announce Type: new Abstract: Probabilistic model checking for Markov decision processes (MDPs) provides quantitative guarantees, but often offers limited insight into why undesired outcomes occur.

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 AI.

Hugging Face Trending Papers

Jun 29

Sample-Efficient Learning of Probabilistic Causes for Reachability in Markov Decision Processes with Probabilistic Guarantees

Probabilistic model checking for Markov decision processes (MDPs) provides quantitative guarantees, but often offers limited insight into why undesired outcomes occur. Probability-raising (PR) causality addresses this by identifying states whose visitation increases the probability of reaching designated states.

reinforcement-learning benchmarks

arXiv AI

Jul 31

Property-driven Causal Abstractions for Markov Decision Processes

arXiv:2607. 26787v1 Announce Type: new Abstract: Markov Decision Processes (MDPs) are widely used as decision-making models, commonly specified over factored state spaces through state variables and their valuations.

By Jule Schmidt, Maximilian Weininger, Clemens Dubslaff, David Parker, Nils Jansen

reinforcement-learning benchmarks

arXiv Machine Learning

Aug 4

Near-Optimal Reinforcement Learning for Constrained Recurrence Objectives

arXiv:2511. 19849v2 Announce Type: replace-cross Abstract: Recurrence objectives, where a target region must be visited infinitely often, are a fundamental class of specifications for Markov decision processes (MDPs) and form the core of $\omega$-regular and linear temporal logic (LTL) objectives.

By Dominik Wagner, Leon Witzman, Luke Ong

reinforcement-learning safety

arXiv Machine Learning

Aug 26

Model-Based Learning of Near-Optimal Finite-Window Policies in POMDPs

arXiv:2604.01024v2 Announce Type: replace Abstract: We study model-based learning of finite-window policies in tabular partially observable Markov decision processes (POMDPs). A common approach to le...

By Philip Jordan, Maryam Kamgarpour

reinforcement-learning

arXiv AI

2d ago

Q-Learning for Reachability in MEC-Free MDPs

The paper introduces Quasar, a model‑free Q‑learning algorithm that guarantees asymptotic convergence for reachability objectives in Markov Decision Processes that are free of non‑terminal maximal end components (MECs). Unlike prior model‑based methods, Quasar does not estimate transition probabilities, reducing memory usage from O(|S|²|A|) to O(|S||A|). Experiments on the Quantitative Verification Benchmark Set show that Quasar converges to optimal policies with far fewer samples than existing state‑of‑the‑art model‑based approaches.

By Lu-Chin Chang, Suguman Bansal

reinforcement-learning efficiency benchmarks

arXiv AI

Jun 2

Robust Shielding for Safe Reinforcement Learning

arXiv:2606. 00270v1 Announce Type: new Abstract: Shielding is an effective approach to formally guarantee the safety of reinforcement learning agents in Markov decision processes (MDPs).

By Edwin Hamel-De le Court, Thom Badings, Alessandro Abate, Francesco Belardinelli, Francesco Fabiano

agents reinforcement-learning safety

One email a morning, machine-written

Related stories

Sample-Efficient Learning of Probabilistic Causes for Reachability in Markov Decision Processes with Probabilistic Guarantees

Property-driven Causal Abstractions for Markov Decision Processes

Near-Optimal Reinforcement Learning for Constrained Recurrence Objectives

Model-Based Learning of Near-Optimal Finite-Window Policies in POMDPs

Q-Learning for Reachability in MEC-Free MDPs

Robust Shielding for Safe Reinforcement Learning