Reinforcement Learning with Demonstrations

Olivier Pietquin (Google Brain)

Date: Monday 19 October 5 PM – 7 PM UTC

Deep Reinforcement Learning (DRL) has recently experienced increasing interest after its success at playing video games such as Atari, DotA or Starcraft II as well as defeating grand masters at Go and Chess. However, many tasks remain hard to solve with DRL, even given almost unlimited compute power and simulation time. These tasks often share the common problem of being “hard exploration tasks”. In this tutorial, we will show how using demonstrations (even sub-optimal) can help in learning policies through different mechanisms such as imitation learning, inverse reinforcement learning, credit assignment and others.