Metraipolis › archive › dc_0eeb24ea926b

Scalable Multi-Task Inverse Reinforcement Learning — arXiv:2610.00758

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.00758
License (as archived)
CC0-1.0
Archived
2026-10-06T15:33:38.165Z
SHA-256 of the archived text
3ecaf1db091211ab4b68c3babab0108792bb6f4309cb4ea5466a06e7018b3b39
Stable URL of this page
https://metraipolis.com/documento/dc_0eeb24ea926b

How to cite

Scalable Multi-Task Inverse Reinforcement Learning — arXiv:2610.00758 — arXiv (en), https://arxiv.org/abs/2610.00758 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0eeb24ea926b (Metraipolis archive dc_0eeb24ea926b, sha256 3ecaf1db091211ab4b68c3babab0108792bb6f4309cb4ea5466a06e7018b3b39)
BibTeX
@misc{dc0eeb24ea926b,
  title = {Scalable Multi-Task Inverse Reinforcement Learning — arXiv:2610.00758},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00758},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0eeb24ea926b; sha256 3ecaf1db091211ab4b68c3babab0108792bb6f4309cb4ea5466a06e7018b3b39},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00758. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

By learning transferable rewards, inverse reinforcement learning (IRL) enables counterfactual evaluation of agents under modified environments. Such transfer places strict requirements on coverage since target environments affect agents' state occupancy. We propose a multi-task IRL method that pools data across multiple agents with different rewards in the same environment under a low-rank assumption. In addition to alleviating coverage requirements, so each task need not visit every state as long as others do, the method offers scalable evaluation of multiple tasks under new environments as computationally intensive planning scales with rank rather than the number of tasks. We provide finite sample guarantees on reward recovery and on policy learning in new environments. Experiments show our method is robust to limited coverage, recovers rewards on and off of each task's support, transfers to target environments at lower regret than baselines, with its computational advantage over per-task methods widening as tasks grow.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-02 in stat.ML).
Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.00758 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T15:12:55.894Z dalla pagina https://arxiv.org/catchup/stat.ML/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).