SALESFORCE Research Speaker

  • Remote Access Enabled
  • Virtual Presentation
Career Presentation

Join STEPHAN ZHENG , Lead Research Scientist at Salesforce Research, for this talk focused on the AI Economist.

Tackling real-world socio-economic challenges requires designing and testing economic policies. However, this is hard in practice, due to a lack of appropriate (micro-level) economic data and limited opportunity to experiment. In Zheng et al., 2020, we propose a two-level deep reinforcement learning approach to learn dynamic tax policies, based on principled economic simulations in which both agents and a social planner (government) learn and adapt. AI social planners can discover tax policies that improve the equality and productivity trade-off by at least 16%, compared to the prominent Saez tax model, US Federal tax, and the free market. The learned tax policies are qualitatively different from the baselines, and certain model instances are effective in human studies as well.

This talk will present three topics: 1) economic policy design in the context of multi-agent RL, 2) our two-level RL approach to economic policy design, and 3) open research problems towards an AI Economist for the real world. These include key methodological challenges in two-level RL and data-driven economic modeling, multi-agent RL, mechanism design, convergence guarantees, robustness, explainability, and others.

More about the Speaker.


Since we can’t meet you on campus this year, we’d love to meet you online instead. Join us for our Salesforce Research Speaker Series to hear from leaders in our AI Research program and discuss opportunities for you to launch your career at Salesforce.   Check out our website to learn more about our Research program, and open roles which may be a fit for your background.

We can't wait to connect at our virtual event to discuss opportunities to launch your future at Salesforce Research.

For More Information, Please Contact: /