Learning to Pick at Non-Zero-Velocity From Interactive Demonstrations

Non-interactive Zero-Knowledge from Homomorphic Encryption

We propose a method for compiling a class of Σ-protocols (3-move public-coin protocols) into non-interactive zero-knowledge arguments. The method is based on homomorphic encryption and does not use random oracles. It only requires that a private/public key pair is set up for the verifier. The method applies to all known discrete-log based Σ-protocols. As applications, we obtain non-interactive ...

Learning from Limited Demonstrations

We propose a Learning from Demonstration (LfD) algorithm which leverages expert data, even if they are very few or inaccurate. We achieve this by using both expert data, as well as reinforcement signals gathered through trial-and-error interactions with the environment. The key idea of our approach, Approximate Policy Iteration with Demonstration (APID), is that expert’s suggestions are used to...

Learning from Demonstrations Through the Use of Non-rigid Registration

We consider the problem of teaching robots by demonstration how to perform manipulation tasks, in which the geometry (including size, shape, and pose) of the relevant objects varies from trial to trial. We present a method, which we call trajectory transfer, for adapting a demonstrated trajectory from the geometry at training time to the geometry at test time. Trajectory transfer is based on no...

Efficient Non - Interactive Zero - Knowledge

Robot Learning from Failed Demonstrations

Robot learning from demonstration (RLfD) seeks to enable lay users to encode desired robot behaviors as autonomous controllers. Current work uses a human’s demonstration of the target task to initialize the robot’s policy, and then improves its performance either through practice (with a known reward function), or additional human interaction. In this article, we focus on the initialization ste...