Contributed Talk
in
Workshop: Learning by Instruction
Assisted Inverse Reinforcement Learning
Adish Singla · Rati Devidze
[
Abstract
]
Abstract:
We study the problem of inverse reinforcement learning (IRL) with the added twist that the learner is assisted by a helpful teacher. More formally, we tackle the following algorithmic question: How could a teacher provide an informative sequence of demonstrations to an IRL agent to speed up the learning process? We prove rigorous convergence guarantees of a new iterative teaching algorithm that adaptively chooses demonstrations based on the learner’s current performance. Extensive experiments with a car driving simulator environment show that the learning progress can be speeded up drastically as compared to an uninformative teacher.
Live content is unavailable. Log in and register to view live content