Timezone: »

Repeated Inverse Reinforcement Learning
Kareem Amin · Nan Jiang · Satinder Singh

Wed Dec 06 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #199

We introduce a novel repeated Inverse Reinforcement Learning problem: the agent has to act on behalf of a human in a sequence of tasks and wishes to minimize the number of tasks that it surprises the human by acting suboptimally with respect to how the human would have acted. Each time the human is surprised, the agent is provided a demonstration of the desired behavior by the human. We formalize this problem, including how the sequence of tasks is chosen, in a few different ways and provide some foundational results.

Author Information

Kareem Amin (Google Research)
Nan Jiang (University of Illinois at Urbana-Champaign)
Satinder Singh (University of Michigan)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors