Learning When to Cooperate Under Heterogeneous Goals
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910045044736000 |
|---|---|
| author | Taylor-Davies, Max Bramley, Neil Lucas, Christopher G. |
| author_facet | Taylor-Davies, Max Bramley, Neil Lucas, Christopher G. |
| contents | A significant element of human cooperative intelligence lies in our ability to identify opportunities for fruitful collaboration; and conversely to recognise when the task at hand is better pursued alone. Research on flexible cooperation in machines has left this meta-level problem largely unexplored, despite its importance for successful collaboration in heterogeneous open-ended environments. Here, we extend the typical Ad Hoc Teamwork (AHT) setting to incorporate the idea of agents having heterogeneous goals that in any given scenario may or may not overlap. We introduce a novel approach to learning policies in this setting, based on a hierarchical combination of imitation and reinforcement learning, and show that it outperforms baseline methods across extended versions of two cooperative environments. We also investigate the contribution of an auxiliary component that learns to model teammates by predicting their actions, finding that its effect on performance is inversely related to the amount of observable information about teammate goals. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07253 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learning When to Cooperate Under Heterogeneous Goals Taylor-Davies, Max Bramley, Neil Lucas, Christopher G. Multiagent Systems Artificial Intelligence A significant element of human cooperative intelligence lies in our ability to identify opportunities for fruitful collaboration; and conversely to recognise when the task at hand is better pursued alone. Research on flexible cooperation in machines has left this meta-level problem largely unexplored, despite its importance for successful collaboration in heterogeneous open-ended environments. Here, we extend the typical Ad Hoc Teamwork (AHT) setting to incorporate the idea of agents having heterogeneous goals that in any given scenario may or may not overlap. We introduce a novel approach to learning policies in this setting, based on a hierarchical combination of imitation and reinforcement learning, and show that it outperforms baseline methods across extended versions of two cooperative environments. We also investigate the contribution of an auxiliary component that learns to model teammates by predicting their actions, finding that its effect on performance is inversely related to the amount of observable information about teammate goals. |
| title | Learning When to Cooperate Under Heterogeneous Goals |
| topic | Multiagent Systems Artificial Intelligence |
| url | https://arxiv.org/abs/2603.07253 |