What is the Solution for State-Adversarial Multi-Agent Reinforcement Learning?
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914750686822400 |
|---|---|
| author | Han, Songyang Su, Sanbao He, Sihong Han, Shuo Yang, Haizhao Zou, Shaofeng Miao, Fei |
| author_facet | Han, Songyang Su, Sanbao He, Sihong Han, Shuo Yang, Haizhao Zou, Shaofeng Miao, Fei |
| contents | Various methods for Multi-Agent Reinforcement Learning (MARL) have been developed with the assumption that agents' policies are based on accurate state information. However, policies learned through Deep Reinforcement Learning (DRL) are susceptible to adversarial state perturbation attacks. In this work, we propose a State-Adversarial Markov Game (SAMG) and make the first attempt to investigate different solution concepts of MARL under state uncertainties. Our analysis shows that the commonly used solution concepts of optimal agent policy and robust Nash equilibrium do not always exist in SAMGs. To circumvent this difficulty, we consider a new solution concept called robust agent policy, where agents aim to maximize the worst-case expected state value. We prove the existence of robust agent policy for finite state and finite action SAMGs. Additionally, we propose a Robust Multi-Agent Adversarial Actor-Critic (RMA3C) algorithm to learn robust policies for MARL agents under state uncertainties. Our experiments demonstrate that our algorithm outperforms existing methods when faced with state perturbations and greatly improves the robustness of MARL policies. Our code is public on https://songyanghan.github.io/what_is_solution/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2212_02705 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | What is the Solution for State-Adversarial Multi-Agent Reinforcement Learning? Han, Songyang Su, Sanbao He, Sihong Han, Shuo Yang, Haizhao Zou, Shaofeng Miao, Fei Artificial Intelligence Computer Science and Game Theory Multiagent Systems Various methods for Multi-Agent Reinforcement Learning (MARL) have been developed with the assumption that agents' policies are based on accurate state information. However, policies learned through Deep Reinforcement Learning (DRL) are susceptible to adversarial state perturbation attacks. In this work, we propose a State-Adversarial Markov Game (SAMG) and make the first attempt to investigate different solution concepts of MARL under state uncertainties. Our analysis shows that the commonly used solution concepts of optimal agent policy and robust Nash equilibrium do not always exist in SAMGs. To circumvent this difficulty, we consider a new solution concept called robust agent policy, where agents aim to maximize the worst-case expected state value. We prove the existence of robust agent policy for finite state and finite action SAMGs. Additionally, we propose a Robust Multi-Agent Adversarial Actor-Critic (RMA3C) algorithm to learn robust policies for MARL agents under state uncertainties. Our experiments demonstrate that our algorithm outperforms existing methods when faced with state perturbations and greatly improves the robustness of MARL policies. Our code is public on https://songyanghan.github.io/what_is_solution/. |
| title | What is the Solution for State-Adversarial Multi-Agent Reinforcement Learning? |
| topic | Artificial Intelligence Computer Science and Game Theory Multiagent Systems |
| url | https://arxiv.org/abs/2212.02705 |