Scalable Constrained Policy Optimization for Safe Multi-agent Reinforcement Learning
–Neural Information Processing Systems
A challenging problem in seeking to bring multi-agent reinforcement learning (MARL) techniques into real-world applications, such as autonomous driving and drone swarms, is how to control multiple agents safely and cooperatively to accomplish tasks.
Neural Information Processing Systems
May-25-2025, 21:17:19 GMT
- Country:
- Asia > China > Shanxi Province (0.14)
- Genre:
- Research Report
- Experimental Study (0.93)
- New Finding (0.92)
- Research Report
- Industry:
- Energy > Power Industry (0.45)
- Information Technology (0.66)
- Technology: