Safe Learning Under Irreversible Dynamics via Asking for Help — Paper

Abstract

-cross Abstract: Most learning algorithms with formal regret guarantees essentially rely on trying all possible behaviors, which is problematic when some errors cannot be recovered from. Instead, we allow the learning agent to ask for help from a mentor and to transfer knowledge between similar states. We show that this combination enables the agent to learn both safely and effectively. Under standard online learning assumptions, we provide an algorithm whose regret and number of mentor queries are both sublinear in the time horizon for Markov decision processes with irreversible dynamics and infinite state spaces. Our proof involves a sequence of three reductions, making our result more general than a single algorithm. Conceptually, our result may be the first formal proof that it is possible for an agent to obtain high reward while becoming self-sufficient in an unknown, unbounded, and high-stakes environment without resets.

Authors 4

Benjamin Plaut, Juan Li\'evano-Karim, Hanlin Zhu, Stuart Russell

Specification

Official page: arxiv.org/abs/2502.14043
Source:arXiv (Atom API + RSS)T1observed 2 h agohigh
Arxiv announce type: replace
Source:arXiv (Atom API + RSS)T1observed 2 h agohigh
arXiv id: 2502.14043
Source:arXiv (Atom API + RSS)T1observed 2 h agohigh
Categories: cs.LG, cs.AI
Source:arXiv (Atom API + RSS)T1observed 2 h agohigh
PDF: arxiv.org/pdf/2502.14043
Source:arXiv (Atom API + RSS)T1observed 2 h agohigh
Primary category: cs.LG
Source:arXiv (Atom API + RSS)T1observed 2 h agohigh
Published: 11 Sept 2026
Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

2 h ago

Conflicts

None

No models linked to this paper yet.

Authors: Benjamin Plaut, Juan Li\'evano-Karim, Hanlin Zhu

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history · Official page

1 claims · 1 propertiesShow all properties

Official pageofficial_url1

Claim history for Official page
Value	Valid from → to	Status	Source	Confidence	Extractor
https://arxiv.org/abs/2502.14043	11 Sept 2026 21:03 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

11 Sept 2026
New paperPaperSafe Learning Under Irreversible Dynamics via Asking for Help
New paper: Safe Learning Under Irreversible Dynamics via Asking for Help
arxiv
rss.arxiv.org

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
arXiv (Atom API + RSS)	rss.arxiv.org/rss/cs.AI	feed	T1· Official	2 h ago	1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.