In this work, we take a fresh look at some old and new algorithms for off-policy, return-based reinforcement learning. Expressing these in a common form, we derive a novel algorithm, Retrace(λ), with three desired properties: (1) it has low variance; (2) it safely uses samples collected from any behaviour policy, whatever its degree of "off-policyness"; and (3) it is efficient as it makes the best use of samples collected from near on-policy behaviour policies. We analyze the contractive nature of the related operator under both off-policy policy evaluation and control settings and derive online sample-based algorithms. We believe this is the first return-based off-policy control algorithm converging a.s. to Q

CIRL, and derive an approximate CIRL algorithm.

W eighted minwise hashing (WMH) is one of the fundamental subroutine, required by many celebrated approximation algorithms, commonly adopted in industrial practice for large -scale search and learning.

We introduce self-normalizing neural networks (SNNs) to enable high-level abstract representations.

The word/phrase pairs in this evaluation dataset are collected from the click data with millions of users in an image search system, thus contain rich semantic relationships.

We introduce the value iteration network (VIN): a fully differentiable neural network with a'planning module' embedded within.

We also introduce a semi-supervised approach, termed discriminative CSFA (dCSFA).

Neural Information Processing Systems http://nips.cc/

We present a new type of probabilistic model which we call DISsimilarity COefficient Networks (DISCO Nets).

This was proposed and named by Tibshirani et al. (2005),