We introduce new planning and reinforcement learning algorithms for
discounted MDPs that utilize an approximate model of the environment to
accelerate the convergence of the value function. Inspired by the splitting
approach in numerical linear algebra, we introduce Operator Splitting Value
Iteration (OS-VI) for both Policy Evaluation and Control problems. OS-VI
achieves a much faster convergence rate when the model is accurate enough. We
also introduce a sample-based version of the algorithm called OS-Dyna. Unlike
the traditional Dyna architecture, OS-Dyna still converges to the correct value
function in presence of model approximation error.

介绍一种基于近似环境模型的规划与强化学习算法，名为 Operator Splitting Value Iteration (OS-VI)，能更快地达到收敛，同时提出了针对采样的版本 OS-Dyna 用于处理模型误差问题。

运算分裂价值迭代

Operator Splitting Value Iteration

Fast estimates of model uncertainty are required for many robust robotics
applications. Deep Ensembles provides state of the art uncertainty without
requiring Bayesian methods, but still it is computationally expensive. In this
paper we propose deep sub-ensembles, an approximation to deep ensembles where
the core idea is to ensemble only the layers close to the output, and not the
whole model. With ResNet-20 on the CIFAR10 dataset, we obtain 1.5-2.5 speedup
over a Deep Ensemble, with a small increase in error and NLL, and similarly up
to 5-15 speedup with a VGG-like network on the SVHN dataset. Our results show
that this idea enables a trade-off between error and uncertainty quality versus
computational performance.

该论文提出了一种名为深度子集合（Deep Sub-Ensembles）的方法，通过仅对接近输出层的层进行集成，从而近似获得深度集合（Deep Ensembles）的模型不确定性， 在减少计算负担的同时，控制了误差和 NLL 的变化，来实现在误差和不确定性精度和计算性能之间的权衡。

图像分类快速不确定性估计的深度子整体方法

Deep Sub-Ensembles for Fast Uncertainty Estimation in Image  Classification

High computational complexity hinders the widespread usage of Convolutional
Neural Networks (CNNs), especially in mobile devices. Hardware accelerators are
arguably the most promising approach for reducing both execution time and power
consumption. One of the most important steps in accelerator development is
hardware-oriented model approximation. In this paper we present Ristretto, a
model approximation framework that analyzes a given CNN with respect to
numerical resolution used in representing weights and outputs of convolutional
and fully connected layers. Ristretto can condense models by using fixed point
arithmetic and representation instead of floating point. Moreover, Ristretto
fine-tunes the resulting fixed point network. Given a maximum error tolerance
of 1%, Ristretto can successfully condense CaffeNet and SqueezeNet to 8-bit.
The code for Ristretto is available.

本文提出 Ristretto，一种模型逼近框架，可以使用固定点算术和表示来压缩卷积和全连接层的权重和输出，并且可以通过微调将结果定制到具体的硬件设备，成功地将 CaffeNet 和 SqueezeNet 压缩到 8 位。