Multi-agent Reinforcement Learning with Deep Networks for Diverse Q-Vectors
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910482918539264 |
|---|---|
| author | Luo, Zhenglong Chen, Zhiyong Welsh, James |
| author_facet | Luo, Zhenglong Chen, Zhiyong Welsh, James |
| contents | Multi-agent reinforcement learning (MARL) has become a significant research topic due to its ability to facilitate learning in complex environments. In multi-agent tasks, the state-action value, commonly referred to as the Q-value, can vary among agents because of their individual rewards, resulting in a Q-vector. Determining an optimal policy is challenging, as it involves more than just maximizing a single Q-value. Various optimal policies, such as a Nash equilibrium, have been studied in this context. Algorithms like Nash Q-learning and Nash Actor-Critic have shown effectiveness in these scenarios. This paper extends this research by proposing a deep Q-networks (DQN) algorithm capable of learning various Q-vectors using Max, Nash, and Maximin strategies. The effectiveness of this approach is demonstrated in an environment where dual robotic arms collaborate to lift a pot. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_07848 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-agent Reinforcement Learning with Deep Networks for Diverse Q-Vectors Luo, Zhenglong Chen, Zhiyong Welsh, James Artificial Intelligence Multiagent Systems Multi-agent reinforcement learning (MARL) has become a significant research topic due to its ability to facilitate learning in complex environments. In multi-agent tasks, the state-action value, commonly referred to as the Q-value, can vary among agents because of their individual rewards, resulting in a Q-vector. Determining an optimal policy is challenging, as it involves more than just maximizing a single Q-value. Various optimal policies, such as a Nash equilibrium, have been studied in this context. Algorithms like Nash Q-learning and Nash Actor-Critic have shown effectiveness in these scenarios. This paper extends this research by proposing a deep Q-networks (DQN) algorithm capable of learning various Q-vectors using Max, Nash, and Maximin strategies. The effectiveness of this approach is demonstrated in an environment where dual robotic arms collaborate to lift a pot. |
| title | Multi-agent Reinforcement Learning with Deep Networks for Diverse Q-Vectors |
| topic | Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2406.07848 |