Learning from Multiple Independent Advisors in Multi-agent Reinforcement Learning
Subramanian, Sriram Ganapathi, Taylor, Matthew E., Larson, Kate, Crowley, Mark
–arXiv.org Artificial Intelligence
Multi-agent reinforcement learning typically suffers from the problem of sample inefficiency, where learning suitable policies involves the use of many data samples. Learning from external demonstrators is a possible solution that mitigates this problem. However, most prior approaches in this area assume the presence of a single demonstrator. Leveraging multiple knowledge sources (i.e., advisors) with expertise in distinct aspects of the environment could substantially speed up learning in complex environments. This paper considers the problem of simultaneously learning from multiple independent advisors in multi-agent reinforcement learning. The approach leverages a two-level Q-learning architecture, and extends this framework from single-agent to multi-agent settings. We provide principled algorithms that incorporate a set of advisors by both evaluating the advisors at each state and subsequently using the advisors to guide action selection. We also provide theoretical convergence and sample complexity guarantees. Experimentally, we validate our approach in three different test-beds and show that our algorithms give better performances than baselines, can effectively integrate the combined expertise of different advisors, and learn to ignore bad advice.
arXiv.org Artificial Intelligence
Mar-2-2023
- Country:
- South America
- Brazil > São Paulo (0.04)
- Argentina > Pampas
- Buenos Aires F.D. > Buenos Aires (0.04)
- Oceania
- New Zealand > North Island
- Auckland Region > Auckland (0.04)
- Australia > Victoria
- Melbourne (0.04)
- New Zealand > North Island
- North America
- United States
- Nevada (0.04)
- New Jersey > Middlesex County
- New Brunswick (0.04)
- Colorado > Denver County
- Denver (0.04)
- Hawaii > Honolulu County
- Honolulu (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- California > Los Angeles County
- Long Beach (0.04)
- Massachusetts > Hampshire County
- Amherst (0.04)
- Washington > King County
- Bellevue (0.04)
- New York > New York County
- New York City (0.04)
- Canada
- Ontario
- Waterloo Region > Waterloo (0.14)
- Toronto (0.04)
- British Columbia > Metro Vancouver Regional District
- Vancouver (0.14)
- Alberta > Census Division No. 11
- Edmonton Metropolitan Region > Edmonton (0.04)
- Ontario
- United States
- Europe
- Czechia > Prague (0.04)
- United Kingdom > England
- Greater London > London (0.04)
- Cambridgeshire > Cambridge (0.04)
- Sweden > Stockholm
- Stockholm (0.04)
- France > Grand Est
- Meurthe-et-Moselle > Nancy (0.04)
- Asia
- Middle East > Jordan (0.04)
- Japan (0.04)
- Taiwan > Taiwan Province
- Taipei (0.04)
- South Korea > Seoul
- Seoul (0.04)
- South America
- Genre:
- Research Report > New Finding (0.46)
- Industry:
- Leisure & Entertainment > Games (0.67)
- Government
- Regional Government (0.70)
- Voting & Elections (0.60)
- Technology: