Exploration Through Introspection: A Self-Aware Reward Model
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914237743366144 |
|---|---|
| author | Petrowski, Michael Gašić, Milica |
| author_facet | Petrowski, Michael Gašić, Milica |
| contents | Understanding how artificial agents model internal mental states is central to advancing Theory of Mind in AI. Evidence points to a unified system for self- and other-awareness. We explore this self-awareness by having reinforcement learning agents infer their own internal states in gridworld environments. Specifically, we introduce an introspective exploration component that is inspired by biological pain as a learning signal by utilizing a hidden Markov model to infer "pain-belief" from online observations. This signal is integrated into a subjective reward function to study how self-awareness affects the agent's learning abilities. Further, we use this computational framework to investigate the difference in performance between normal and chronic pain perception models. Results show that introspective agents in general significantly outperform standard baseline agents and can replicate complex human-like behaviors. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_03389 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Exploration Through Introspection: A Self-Aware Reward Model Petrowski, Michael Gašić, Milica Artificial Intelligence Machine Learning Understanding how artificial agents model internal mental states is central to advancing Theory of Mind in AI. Evidence points to a unified system for self- and other-awareness. We explore this self-awareness by having reinforcement learning agents infer their own internal states in gridworld environments. Specifically, we introduce an introspective exploration component that is inspired by biological pain as a learning signal by utilizing a hidden Markov model to infer "pain-belief" from online observations. This signal is integrated into a subjective reward function to study how self-awareness affects the agent's learning abilities. Further, we use this computational framework to investigate the difference in performance between normal and chronic pain perception models. Results show that introspective agents in general significantly outperform standard baseline agents and can replicate complex human-like behaviors. |
| title | Exploration Through Introspection: A Self-Aware Reward Model |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2601.03389 |