Timezone: »

Assisted Inverse Reinforcement Learning
Adish Singla · Rati Devidze

Sat Dec 08 01:15 PM -- 01:30 PM (PST) @

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.

Author Information

Adish Singla (MPI-SWS)
Rati Devidze (MPI-SWS)

More from the Same Authors