Artificial Empathy: Towards a Framework for Unsupervised Agency Detection and Policy Reconstruction
On the map: Deep reinforcement learning methods → Deep RL algorithms and representations
Abstract (arXiv)
We study how an AI system can identify and model other agents in its environment from observation alone, which is a capability necessary for cooperative behaviour in the real world. This problem is less constrained than inverse reinforcement learning and remains largely unexplored. We propose a framework that uses a reinforcement learning agent, trained on an independent task as a prior about agentic dynamics, to perform agency detection and policy reconstruction.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 3 of its 16 references that are in the map. First posted on arXiv 24 Aug 2026.
Builds on
3 of 16 references.
References · 3
- 2013Auto-Encoding Variational Bayescited by 4,053
- 2025Training Agents Inside of Scalable World Modelscited by 136
- 2024Towards Safe and Honest AI Agents with Neural Self-Other Overlapcited by 6
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Artificial Agency Program: Curiosity, compression, and communication in agents
- 2025ProToM: Promoting Prosocial Behaviour via Theory of Mind-Informed Feedback
- 2018Learning Policy Representations in Multiagent Systems
- 2026Agent-Reflex: Teaching Language Agents to Act Reflectively
- 2024Agent AI: Surveying the Horizons of Multimodal Interaction
- 2020Action and Perception as Divergence Minimization
- 2024Empathic Coupling of Homeostatic States for Intrinsic Prosociality
- 2025Sorrel: A simple and flexible framework for multi-agent reinforcement learning