Evolutionary Reinforcement Learning (ERL)
Deep Reinforcement Learning (DRL) algorithms have been successfully applied to a range of challenging control tasks. However, these methods typically suffer from three core difficulties: temporal credit assignment with sparse rewards, lack of effective exploration, and brittle convergence properties that are extremely sensitive to hyperparameters. Collectively, these challenges severely limit the applicability of these approaches to real world problems. Evolutionary Algorithms (EAs), a class of black box optimization techniques inspired by natural evolution, are well suited to address each of these three challenges. However, EAs typically suffer with high sample complexity and struggle to solve problems that require optimization of a large number of parameters. In this paper, we introduce Evolutionary Reinforcement Learning (ERL), a hybrid algorithm that leverages the population of an EA to provide diversified data to train an RL agent, and reinserts the RL agent into the EA population periodically to inject gradient information into the EA. ERL inherits EA’s ability of temporal credit assignment with a fitness metric, effective exploration with a diverse set of policies, and stability of a population-based approach and complements it with off-policy DRL’s ability to leverage gradients for higher sample efficiency and faster learning. Experiments in a range of challenging continuous control benchmark tasks demonstrate that ERL significantly outperforms prior DRL and EA methods, achieving state-of-the-art performances. …

Discriminative Differentiable Dynamic Time Warping (D^3TW)
We address weakly-supervised action alignment and segmentation in videos, where only the order of occurring actions is available during training. We propose Discriminative Differentiable Dynamic Time Warping (D${}^3$TW), which is the first discriminative model for weak ordering supervision. This allows us to bypass the degenerated sequence problem usually encountered in previous work. The key technical challenge for discriminative modeling with weak-supervision is that the loss function of the ordering supervision is usually formulated using dynamic programming and is thus not differentiable. We address this challenge by continuous relaxation of the min-operator in dynamic programming and extend the DTW alignment loss to be differentiable. The proposed D${}^3$TW innovatively solves sequence alignment with discriminative modeling and end-to-end training, which substantially improves the performance in weakly supervised action alignment and segmentation tasks. We show that our model outperforms the current state-of-the-art across three evaluation metrics in two challenging datasets. …

Arc Diagram
In graph drawing, an arc diagram is a style of graph drawing, in which the vertices of a graph are placed along a line in the Euclidean plane, with edges being drawn as semicircles in one of the two halfplanes bounded by the line, or as smooth curves formed by sequences of semicircles. In some cases, line segments of the line itself are also allowed as edges, as long as they connect only vertices that are consecutive along the line. …

ReSet
Neural Network is a powerful Machine Learning tool that shows outstanding performance in Computer Vision, Natural Language Processing, and Artificial Intelligence. In particular, recently proposed ResNet architecture and its modifications produce state-of-the-art results in image classification problems. ResNet and most of the previously proposed architectures have a fixed structure and apply the same transformation to all input images. In this work, we develop a ResNet-based model that dynamically selects Computational Units (CU) for each input object from a learned set of transformations. Dynamic selection allows the network to learn a sequence of useful transformations and apply only required units to predict the image label. We compare our model to ResNet-38 architecture and achieve better results than the original ResNet on CIFAR-10.1 test set. While examining the produced paths, we discovered that the network learned different routes for images from different classes and similar routes for similar images. …