In this paper, we will show how a robot can follow a developmental program to learn new tasks and even some rudimentary language skills. The learner will start ...

Abstract: We present a system to learn task representations from ambiguous feedback. We consider an inverse reinforcement learner that receives feedback ...

The system needs to estimate simultaneously what the task is, and how the user is providing the feedback. We further explore the problem of ambiguous protocols ...

PDF | We present a system to learn task representations from ambiguous feedback. We consider an inverse reinforcement learner that receives feedback.

The system needs to estimate simultaneously what the task is (i.e. how to find a compact representation to the task goal), and how the teacher is providing the ...

Simultaneous Acquisition of Task and Feedback Models, Manuel Lopes, Thomas. Cederborg and Pierre-Yves Oudeyer, ICDL, 2011. Page 14. Markov decision process.

Computational results are presented that show that it is possible to learn the task under a noisy and ambiguous feedback and the system is able to reduce ...

We extend previous approaches by learning simultaneously how the feedback is being provided and what is the meaning of the teacher's feedback signs. Note that ...

Simultaneous acquisition of the task and the feedback models with three different exploration methods for a problem with 225 states. The figures show the ...

Apr 9, 2021 · Manuel Lopes , Thomas Cederbourg, Pierre-Yves Oudeyer: Simultaneous acquisition of task and feedback models. ICDL-EPIROB 2011: 1-7.