Newness and distinctiveness is claimed in the features of ornamentation as shown inside the broken line circle in the accompanying representation.

Display screen or portion thereof with graphical user interface

The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent years. Contrary to conventional approaches to AI where tasks are solved from scratch using a fixed learning algorithm, meta-learning aims to improve the learning algorithm itself, given the experience of multiple learning episodes. This paradigm provides an opportunity to tackle many conventional challenges of deep learning, including data and computation bottlenecks, as well as generalization. This survey describes the contemporary meta-learning landscape. We first discuss definitions of meta-learning and position it with respect to related fields, such as transfer learning and hyperparameter optimization. We then propose a new taxonomy that provides a more comprehensive breakdown of the space of meta-learning methods today. We survey promising applications and successes of meta-learning such as few-shot learning and reinforcement learning. Finally, we discuss outstanding challenges and promising areas for future research.

Meta-Learning in Neural Networks: A Survey

/pdf/meta-world-a-benchmark-and-evaluation-for-multi-task-and-wom9oupayh.pdf

Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning

First-person vision is gaining interest as it offers a unique viewpoint on people’s interaction with objects, their attention, and even intention. However, progress in this challenging domain has been relatively slow due to the lack of sufficiently large datasets. In this paper, we introduce Open image in new window , a large-scale egocentric video benchmark recorded by 32 participants in their native kitchen environments. Our videos depict non-scripted daily activities: we simply asked each participant to start recording every time they entered their kitchen. Recording took place in 4 cities (in North America and Europe) by participants belonging to 10 different nationalities, resulting in highly diverse cooking styles. Our dataset features 55h of video consisting of 11.5M frames, which we densely labelled for a total of 39.6K action segments and 454.3K object bounding boxes. Our annotation is unique in that we had the participants narrate their own videos (after recording), thus reflecting true intention, and we crowd-sourced ground-truths based on these. We describe our object, action and anticipation challenges, and evaluate several baselines over two test splits, seen and unseen kitchens.

/pdf/scaling-egocentric-vision-the-epic-kitchens-dataset-3jqhdcd0n4.pdf

Scaling Egocentric Vision: The EPIC-KITCHENS Dataset

In the context of robotics and automation, learning from demonstration (LfD) is the paradigm in which robots acquire new skills by learning to imitate an expert. The choice of LfD over other robot ...

/pdf/recent-advances-in-robot-learning-from-demonstration-2r1vs09iql.pdf

Recent Advances in Robot Learning from Demonstration

Imitation learning is a powerful paradigm for robot skill acquisition. However, obtaining demonstrations suitable for learning a policy that maps from raw pixels to actions can be challenging. In this paper we describe how consumer-grade Virtual Reality headsets and hand tracking hardware can be used to naturally teleoperate robots to perform complex tasks. We also describe how imitation learning can learn deep neural network policies (mapping from pixels to actions) that can acquire the demonstrated skills. Our experiments showcase the effectiveness of our approach for learning visuomotor skills.

Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation

Credit assignment in Meta-reinforcement learning (Meta-RL) is still poorly understood. Existing methods either neglect credit assignment to pre-adaptation behavior or implement it naively. This leads to poor sample-efficiency during meta-training as well as ineffective task identification strategies. This paper provides a theoretical analysis of credit assignment in gradient-based Meta-RL. Building on the gained insights we develop a novel meta-learning algorithm that overcomes both the issue of poor credit assignment and previous difficulties in estimating meta-policy gradients. By controlling the statistical distance of both pre-adaptation and adapted policies during meta-policy search, the proposed algorithm endows efficient and stable meta-learning. Our approach leads to superior pre-adaptation policy behavior and consistently outperforms previous Meta-RL algorithms in sample-efficiency, wall-clock time, and asymptotic performance.

/pdf/promp-proximal-meta-policy-search-3m9n8b7cwq.pdf

ProMP: Proximal Meta-Policy Search

A computer-implemented system, method and computer readable medium to generate graphical visualizations corresponding to a data set populated in a web-based document, such as a spreadsheet. The spreadsheet is accessible in an interne or cloud-based system, and enables users to automatically create graphical visualizations or representations based on recommendations by a spreadsheet application. The graphical visualizations may be automatically ranked such that the system provides the recommendations to the user for display. Automatic ranking is accomplished, for example, by determining data types from identifying column type, differentiating column types, and extracting data sets having attributes corresponding to various graphical visualizations.

Ranking graphical visualizations of a data set according to data attributes

We present a novel modular architecture for StarCraft II AI. The architecture splits responsibilities between multiple modules that each control one aspect of the game, such as buildorder selection or tactics. A centralized scheduler reviews macros suggested by all modules and decides their order of execution. An updater keeps track of environment changes and instantiates macros into series of executable actions. Modules in this framework can be optimized independently or jointly via human design, planning, or reinforcement learning. We present the first result of applying deep reinforcement learning techniques to training a modular agent with selfplay, achieving 92% or 86% win rates against the ”Harder” (level 5) built-in Blizzard bot in Zerg vs. Zerg matches, with or without fog-of-war.

Dennis Lee

Papers

Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation

ProMP: Proximal Meta-Policy Search

ProMP: Proximal Meta-Policy Search

Ranking graphical visualizations of a data set according to data attributes

Modular Architecture for StarCraft II with Deep Reinforcement Learning