On the Complexity of Learning to Cooperate with Populations of Socially Rational Agents
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911939113779200 |
|---|---|
| author | Loftin, Robert Bandyopadhyay, Saptarashmi Çelikok, Mustafa Mert |
| author_facet | Loftin, Robert Bandyopadhyay, Saptarashmi Çelikok, Mustafa Mert |
| contents | Artificially intelligent agents deployed in the real-world will require the ability to reliably \textit{cooperate} with humans (as well as other, heterogeneous AI agents). To provide formal guarantees of successful cooperation, we must make some assumptions about how partner agents could plausibly behave. Any realistic set of assumptions must account for the fact that other agents may be just as adaptable as our agent is. In this work, we consider the problem of cooperating with a \textit{population} of agents in a finitely-repeated, two player general-sum matrix game with private utilities. Two natural assumptions in such settings are that: 1) all agents in the population are individually rational learners, and 2) when any two members of the population are paired together, with high-probability they will achieve at least the same utility as they would under some Pareto efficient equilibrium strategy. Our results first show that these assumptions alone are insufficient to ensure \textit{zero-shot} cooperation with members of the target population. We therefore consider the problem of \textit{learning} a strategy for cooperating with such a population using prior observations its members interacting with one another. We provide upper and lower bounds on the number of samples needed to learn an effective cooperation strategy. Most importantly, we show that these bounds can be much stronger than those arising from a "naive'' reduction of the problem to one of imitation learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_00419 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On the Complexity of Learning to Cooperate with Populations of Socially Rational Agents Loftin, Robert Bandyopadhyay, Saptarashmi Çelikok, Mustafa Mert Machine Learning Artificial Intelligence Computer Science and Game Theory Multiagent Systems Artificially intelligent agents deployed in the real-world will require the ability to reliably \textit{cooperate} with humans (as well as other, heterogeneous AI agents). To provide formal guarantees of successful cooperation, we must make some assumptions about how partner agents could plausibly behave. Any realistic set of assumptions must account for the fact that other agents may be just as adaptable as our agent is. In this work, we consider the problem of cooperating with a \textit{population} of agents in a finitely-repeated, two player general-sum matrix game with private utilities. Two natural assumptions in such settings are that: 1) all agents in the population are individually rational learners, and 2) when any two members of the population are paired together, with high-probability they will achieve at least the same utility as they would under some Pareto efficient equilibrium strategy. Our results first show that these assumptions alone are insufficient to ensure \textit{zero-shot} cooperation with members of the target population. We therefore consider the problem of \textit{learning} a strategy for cooperating with such a population using prior observations its members interacting with one another. We provide upper and lower bounds on the number of samples needed to learn an effective cooperation strategy. Most importantly, we show that these bounds can be much stronger than those arising from a "naive'' reduction of the problem to one of imitation learning. |
| title | On the Complexity of Learning to Cooperate with Populations of Socially Rational Agents |
| topic | Machine Learning Artificial Intelligence Computer Science and Game Theory Multiagent Systems |
| url | https://arxiv.org/abs/2407.00419 |