Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2602.16301 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910025682780160 |
|---|---|
| author | Weis, Marissa A. Wołczyk, Maciej Nasser, Rajai Saurous, Rif A. Arcas, Blaise Agüera y Sacramento, João Meulemans, Alexander |
| author_facet | Weis, Marissa A. Wołczyk, Maciej Nasser, Rajai Saurous, Rif A. Arcas, Blaise Agüera y Sacramento, João Meulemans, Alexander |
| contents | Achieving cooperation among self-interested agents remains a fundamental challenge in multi-agent reinforcement learning. Recent work showed that mutual cooperation can be induced between "learning-aware" agents that account for and shape the learning dynamics of their co-players. However, existing approaches typically rely on hardcoded, often inconsistent, assumptions about co-player learning rules or enforce a strict separation between "naive learners" updating on fast timescales and "meta-learners" observing these updates. Here, we demonstrate that the in-context learning capabilities of sequence models allow for co-player learning awareness without requiring hardcoded assumptions or explicit timescale separation. We show that training sequence model agents against a diverse distribution of co-players naturally induces in-context best-response strategies, effectively functioning as learning algorithms on the fast intra-episode timescale. We find that the cooperative mechanism identified in prior work-where vulnerability to extortion drives mutual shaping-emerges naturally in this setting: in-context adaptation renders agents vulnerable to extortion, and the resulting mutual pressure to shape the opponent's in-context learning dynamics resolves into the learning of cooperative behavior. Our results suggest that standard decentralized reinforcement learning on sequence models combined with co-player diversity provides a scalable path to learning cooperative behaviors. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_16301 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Multi-agent cooperation through in-context co-player inference Weis, Marissa A. Wołczyk, Maciej Nasser, Rajai Saurous, Rif A. Arcas, Blaise Agüera y Sacramento, João Meulemans, Alexander Artificial Intelligence Achieving cooperation among self-interested agents remains a fundamental challenge in multi-agent reinforcement learning. Recent work showed that mutual cooperation can be induced between "learning-aware" agents that account for and shape the learning dynamics of their co-players. However, existing approaches typically rely on hardcoded, often inconsistent, assumptions about co-player learning rules or enforce a strict separation between "naive learners" updating on fast timescales and "meta-learners" observing these updates. Here, we demonstrate that the in-context learning capabilities of sequence models allow for co-player learning awareness without requiring hardcoded assumptions or explicit timescale separation. We show that training sequence model agents against a diverse distribution of co-players naturally induces in-context best-response strategies, effectively functioning as learning algorithms on the fast intra-episode timescale. We find that the cooperative mechanism identified in prior work-where vulnerability to extortion drives mutual shaping-emerges naturally in this setting: in-context adaptation renders agents vulnerable to extortion, and the resulting mutual pressure to shape the opponent's in-context learning dynamics resolves into the learning of cooperative behavior. Our results suggest that standard decentralized reinforcement learning on sequence models combined with co-player diversity provides a scalable path to learning cooperative behaviors. |
| title | Multi-agent cooperation through in-context co-player inference |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2602.16301 |