Newest papers

Asymmetric On-Policy Distillation Learns In-Context Exploration

Sriyash Poddar, Yanda Bao, Jacob Krantz, Matthew Chang, Xavier Puig, Roozbeh Mottaghi, Natasha Jaques, Abhishek Gupta · 2026 · arXiv

DOI: 10.48550/arXiv.2610.30105 · open-access PDF

Spanish

La toma de decisiones secuenciales bajo la observación parcial es difícil porque los agentes deben explorar para inferir información oculta, relevante para la tarea antes de actuar de manera efectiva. Aprender tales comportamientos de recopilación de información tabula rasa a través del aprendizaje de reforzamiento en línea es inefectivo, mientras que la imitación en línea media las acciones de expertos en estados ocultos y no aprende exploración. En este trabajo, proponemos ASTEROID, un marco de aprendizaje simple y eficaz estudiante-profesor supervisado que puede aprender exploración en tiempo de prueba. Aunque un experto privilegiado nunca necesita explorar, demostramos que

Machine translation (Meta M2M100); the English original follows.

Abstract

Sequential decision-making under partial observability is difficult because agents must explore to infer hidden, task-relevant information before acting effectively. Learning such information-gathering behaviors tabula rasa via online reinforcement learning is sample-inefficient, whereas offline imitation averages expert actions across hidden states and fails to learn exploration. In this work, we propose ASTEROID, a simple and effective student--teacher supervised learning framework that can learn test-time exploration. Although a privileged expert never needs to explore, we demonstrate that

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.30105, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange