Communicating Unexpectedness for Out-of-Distribution Multi-Agent Reinforcement Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910769692540928 |
|---|---|
| author | Lee, Min Whoo Kim, Kibeom Shin, Soo Wung Lee, Minsu Zhang, Byoung-Tak |
| author_facet | Lee, Min Whoo Kim, Kibeom Shin, Soo Wung Lee, Minsu Zhang, Byoung-Tak |
| contents | Applying multi-agent reinforcement learning methods to realistic settings is challenging as it may require the agents to quickly adapt to unexpected situations that are rarely or never encountered in training. Recent methods for generalization to such out-of-distribution settings are limited to more specific, restricted instances of distribution shifts. To tackle adaptation to distribution shifts, we propose Unexpected Encoding Scheme, a novel decentralized multi-agent reinforcement learning algorithm where agents communicate "unexpectedness," the aspects of the environment that are surprising. In addition to a message yielded by the original reward-driven communication, each agent predicts the next observation based on previous experience, measures the discrepancy between the prediction and the actually encountered observation, and encodes this discrepancy as a message. Experiments on multi-robot warehouse environment support that our proposed method adapts robustly to dynamically changing training environments as well as out-of-distribution environment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_01140 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Communicating Unexpectedness for Out-of-Distribution Multi-Agent Reinforcement Learning Lee, Min Whoo Kim, Kibeom Shin, Soo Wung Lee, Minsu Zhang, Byoung-Tak Multiagent Systems Applying multi-agent reinforcement learning methods to realistic settings is challenging as it may require the agents to quickly adapt to unexpected situations that are rarely or never encountered in training. Recent methods for generalization to such out-of-distribution settings are limited to more specific, restricted instances of distribution shifts. To tackle adaptation to distribution shifts, we propose Unexpected Encoding Scheme, a novel decentralized multi-agent reinforcement learning algorithm where agents communicate "unexpectedness," the aspects of the environment that are surprising. In addition to a message yielded by the original reward-driven communication, each agent predicts the next observation based on previous experience, measures the discrepancy between the prediction and the actually encountered observation, and encodes this discrepancy as a message. Experiments on multi-robot warehouse environment support that our proposed method adapts robustly to dynamically changing training environments as well as out-of-distribution environment. |
| title | Communicating Unexpectedness for Out-of-Distribution Multi-Agent Reinforcement Learning |
| topic | Multiagent Systems |
| url | https://arxiv.org/abs/2501.01140 |