Today we conclude our Black in AI series with this interview with Sicelukwanda Zwane, a masters student at the University of Witwatersrand and graduate research assistant at South Africa's Council for Scientific and Industrial Research or CSIR.
At the workshop, he presented on "Safer Exploration in Deep Reinforcement Learning using Action Priors," which explores transferring action priors between robotic tasks to reduce the exploration space in reinforcement learning, which in turn reduces sample complexity. In our conversation, we discuss what "safer exploration" means in this sense, the difference between this work and other techniques like imitation learning, and how this fits in with the goal of "lifelong learning"
