Learning to Negotiate via Voluntary Commitment
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910882926166016 |
|---|---|
| author | Zhu, Shuhui Wang, Baoxiang Subramanian, Sriram Ganapathi Poupart, Pascal |
| author_facet | Zhu, Shuhui Wang, Baoxiang Subramanian, Sriram Ganapathi Poupart, Pascal |
| contents | The partial alignment and conflict of autonomous agents lead to mixed-motive scenarios in many real-world applications. However, agents may fail to cooperate in practice even when cooperation yields a better outcome. One well known reason for this failure comes from non-credible commitments. To facilitate commitments among agents for better cooperation, we define Markov Commitment Games (MCGs), a variant of commitment games, where agents can voluntarily commit to their proposed future plans. Based on MCGs, we propose a learnable commitment protocol via policy gradients. We further propose incentive-compatible learning to accelerate convergence to equilibria with better social welfare. Experimental results in challenging mixed-motive tasks demonstrate faster empirical convergence and higher returns for our method compared with its counterparts. Our code is available at https://github.com/shuhui-zhu/DCL. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_03866 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning to Negotiate via Voluntary Commitment Zhu, Shuhui Wang, Baoxiang Subramanian, Sriram Ganapathi Poupart, Pascal Artificial Intelligence Computer Science and Game Theory Machine Learning Multiagent Systems The partial alignment and conflict of autonomous agents lead to mixed-motive scenarios in many real-world applications. However, agents may fail to cooperate in practice even when cooperation yields a better outcome. One well known reason for this failure comes from non-credible commitments. To facilitate commitments among agents for better cooperation, we define Markov Commitment Games (MCGs), a variant of commitment games, where agents can voluntarily commit to their proposed future plans. Based on MCGs, we propose a learnable commitment protocol via policy gradients. We further propose incentive-compatible learning to accelerate convergence to equilibria with better social welfare. Experimental results in challenging mixed-motive tasks demonstrate faster empirical convergence and higher returns for our method compared with its counterparts. Our code is available at https://github.com/shuhui-zhu/DCL. |
| title | Learning to Negotiate via Voluntary Commitment |
| topic | Artificial Intelligence Computer Science and Game Theory Machine Learning Multiagent Systems |
| url | https://arxiv.org/abs/2503.03866 |