AI Seminar Series 2022: Shi Dong

The AI Seminar is a weekly meeting at the University of Alberta where researchers interested in artificial intelligence (AI) can share their research. Presenters include both local speakers from the University of Alberta and visitors from other institutions. Topics can be related in any way to artificial intelligence, from foundational theoretical work to innovative applications of AI techniques to new fields and problems.

On April 8, PhD candidate at Stanford University, presented “Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent States," at the AI Seminar.

In the presentation, Dong details a simple reinforcement learning (RL) agent that implements an optimistic version of Q-learning and establishes through regret analysis that this agent can operate with some level of competence in any environment. As time progresses, the agent performs competitively relative to policies that require longer time to evaluate. The time it takes to approach asymptotic performance is polynomial in the complexity of the agent's state representation and the time required to evaluate the best policy that the agent can represent. Notably, there is no dependence on the complexity of the environment. The ultimate per-period performance loss of the agent is bounded by a constant multiple of a measure of distortion introduced by the agent's state representation. Dong explains this work is the first to establish that an algorithm approaches this asymptotic condition within a tractable time frame.

Watch the full presentation below:

Want to learn how you can kick-start your AI career? Find out more about Amii's Career Accelerator to find out more.