Toward Enactive Artificial Intelligence
The paper titled 'Toward Enactive Artificial Intelligence' advocates for integrating enactive approaches to perception and cognition into AI. It contrasts these approaches with classical views that treat perception as a passive process. The authors suggest that mainstream AI has largely overlooked these insights, and they propose a broader incorporation of enactive ideas into AI and reinforcement learning.
- ▪The paper emphasizes the importance of viewing perception as an active engagement with the world.
- ▪It identifies four key enactive concepts relevant to AI: experience, action perception inseparability, autonomy, and embodiment.
- ▪The authors argue that mainstream AI has neglected the dynamic and interactive nature of perception.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2605.24238 (cs) [Submitted on 22 May 2026] Title:Toward Enactive Artificial Intelligence Authors:Banafsheh Rafiee, Richard Sutton View a PDF of the paper titled Toward Enactive Artificial Intelligence, by Banafsheh Rafiee and 1 other authors View PDF HTML (experimental) Abstract:In this paper, we advocate for incorporating enactive approaches to perception and cognition into artificial intelligence (AI). Enactive approaches view perception as an active, skillful engagement with the world, where agents perceive by acting and by understanding how their actions shape their experience.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
