Metraipolis › archive › dc_40826337dfe7
Grounding Insight: An Artificial Affect Signal for Human-Centric Explainability of RL Agents — arXiv:2611.09922
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.09922
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:41:59.880Z
- SHA-256 of the archived text
a9b0b47f66f6783406f97ba32cc452ea1ab98d713a1326e955647b9d5202fcf6- Stable URL of this page
https://metraipolis.com/documento/dc_40826337dfe7
How to cite
Grounding Insight: An Artificial Affect Signal for Human-Centric Explainability of RL Agents — arXiv:2611.09922 — arXiv (en), https://arxiv.org/abs/2611.09922 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_40826337dfe7 (Metraipolis archive dc_40826337dfe7, sha256 a9b0b47f66f6783406f97ba32cc452ea1ab98d713a1326e955647b9d5202fcf6)
BibTeX
@misc{dc40826337dfe7,
title = {Grounding Insight: An Artificial Affect Signal for Human-Centric Explainability of RL Agents — arXiv:2611.09922},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.09922},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_40826337dfe7; sha256 a9b0b47f66f6783406f97ba32cc452ea1ab98d713a1326e955647b9d5202fcf6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09922. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In Human-Interactive Robot Learning (HIRL), human teachers assess learning progress by observing agent behavior. However, Reinforcement Learning (RL) agents often fail to express learning progress in human-interpretable ways, leading to suboptimal or counterproductive teaching. This work proposes "Insight": a human-interpretable affective signal grounded in the RL process. It is specifically designed to address the "Absence of learning" human teacher mental model misalignment - the misconception that a failing or exploring agent is broken, underpowered or not learning at all - by signaling an agent's "Aha!" Insight moment. The signal is derived from the absolute Temporal Difference (TD) error making it easily implementable in other RL agents. To ground this signal, five design criteria were formulated: Relevance, Interpretability, Faithfulness, Scalability, Generalizability. The structural construct validity was assessed through simulation, examining micro and macro dynamics and event-related sensitivity. Micro dynamics reveal that Insight captures meaningful learning events at the appropriate time and magnitude. Macro dynamics demonstrate that the signal follows the agent's learning phases and reflects overall progress. Event-related sensitivity shows, the signal distinguishes the saliency of environment interactions, such as positive rewards versus "trauma-like" negative events. These results demonstrate that technical RL dynamics can be effectively packaged into human-like affective substrates to close the teacher-learner loop. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Human-Computer Interaction (cs.HC) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.09922 — 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 2026-11-10T18:37:37.559Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).