Surprise Minimizing Multi-Agent Learning with Energy-based Models
–Neural Information Processing Systems
Multi-Agent Reinforcement Learning (MARL) has demonstrated significant success by virtue of collaboration across agents. Recent work, on the other hand, introduces surprise which quantifies the degree of change in an agent's environment.
Neural Information Processing Systems
Oct-3-2025, 03:28:02 GMT
- Country:
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.04)
- North America
- Canada > Ontario
- Toronto (0.14)
- United States > New Hampshire
- Hillsborough County > Nashua (0.04)
- Canada > Ontario
- Europe > United Kingdom