Advantage Learning (AL) seeks to increase the action gap between optimal and its competitors, so as improve robustness estimation errors. However, method becomes problematic when induced by approximated value function does not agree with true action. In this paper, we present a novel method, named clipped (clipped AL), address issue. The is inspired our observation that increasing blindly for a...

Most learning algorithms are not invariant to the scale of the function that is being approximated. We propose to adaptively normalize the targets used in learning. This is useful in value-based reinforcement learning, where the magnitude of appropriate value approximations can change over time when we update the policy of behavior. Our main motivation is prior work on learning to play Atari ga...

In many data acquisition systems it is common to observe signals whose amplitudes have been clipped. We present two new algorithms for recovering a clipped signal by leveraging the model assumption that the underlying signal is sparse in the frequency domain. Both algorithms employ ideas commonly used in the field of Compressive Sensing; the first is a modified version of Reweighted `1 minimiza...

This work proposes a multi-dimensional frequency and amplitude estimator tailored for noise corrupted signals that have been clipped. Formulated as a sparse reconstruction problem, the proposed algorithm estimates the signal parameters by solving an atomic norm minimization problem. The estimator also exploits the waveform information provided by the clipped samples, incorporated in the form of...

A high-speed direct-coupled discriminator utilizing emittercoupled integrated circuits is described. The threshold is continuously adjustable between -150 mV and -1.15 V, the pulse pair resolution is 10 nsec, and the maximum continuous repetition rate is 92 MHz. Two modes of operation, clipped and dc , are provided; output widths in the clipped mode are 5 nsec, 10 nsec, or 15 nsec. The use of i...