Timezone: »

Interaction-Grounded Learning
Tengyang Xie · John Langford · Paul Mineiro · Ida Momennejad

Wed Jul 21 06:35 PM -- 06:40 PM (PDT) @

Consider a prosthetic arm, learning to adapt to its user's control signals. We propose \emph{Interaction-Grounded Learning} for this novel setting, in which a learner's goal is to interact with the environment with no grounding or explicit reward to optimize its policies. Such a problem evades common RL solutions which require an explicit reward. The learning agent observes a multidimensional \emph{context vector}, takes an \emph{action}, and then observes a multidimensional \emph{feedback vector}. This multidimensional feedback vector has \emph{no} explicit reward information. In order to succeed, the algorithm must learn how to evaluate the feedback vector to discover a latent reward signal, with which it can ground its policies without supervision. We show that in an Interaction-Grounded Learning setting, with certain natural assumptions, a learner can discover the latent reward and ground its policy for successful interaction. We provide theoretical guarantees and a proof-of-concept empirical evaluation to demonstrate the effectiveness of our proposed approach.

Author Information

Tengyang Xie (University of Illinois at Urbana-Champaign)
John Langford (Microsoft Research)
Paul Mineiro (Microsoft)
Ida Momennejad (Microsoft Research)

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

More from the Same Authors