Berkeley Artificial Intelligence Research (BAIR) has introduced a new reinforcement learning (RL) method, Stochastic Optimal Control with Latent Representations (SOLAR), which can help robots quickly learn tasks such as stacking blocks or pushing objects from visual inputs.
A group of AI experts from top US universities is organizing a sample-efficient reinforcement learning competition, MineRL, which will start on June 1, 2019. The organizers want to increase group participation in reinforcement learning and are encouraging people to “play to benefit science”.
As robots take over industrial manufacturing, specific and accurate robot control is becoming more important. Conventional feedback control methods can effectively solve various types of robot control problems by capturing structures with explicit models such as motion equations.
The Conference on Computer Vision and Pattern Recognition (CVPR) is one of the world’s top computer vision (CV) conferences. CVPR 2019 runs June 15 through June 21 in Long Beach, California, and the list of accepted papers for the prestigious gathering has now been released.
Having notched impressive victories over human professionals in Go, Atari Games, and most recently StarCraft 2 — Google’s DeepMind team has now turned its formidable research efforts to soccer. In a paper released last week, the UK AI company demonstrates a novel machine learning method that trains a team of AI agents to play a simulated version of “the beautiful game.”
Facebook AI Chief Yann LeCun introduced his now-famous “cake analogy” at NIPS 2016: “If intelligence is a cake, the bulk of the cake is unsupervised learning, the icing on the cake is supervised learning, and the cherry on the cake is reinforcement learning (RL).”
Facebook AI Research (FAIR) introduced their own Go bot last year, aiming to reproduce AlphaGo Zero results using their Extensible, Lightweight Framework (ELF) for reinforcement learning research. FAIR recently added new features to ELF OpenGo and has open-sourced the project.
Uber AI Lab has created a buzz in the machine learning community with the publication of a paper introducing a new reinforcement learning algorithm called Go-Explore. The algorithm is designed to overcome the challenges of intelligence exploration in reinforcement learning to improve performance on hard-exploration tasks.
ANYmal does not have an easy life. One of the four-legged robot’s main tasks is to learn how to stand up again — no matter how many times it is kicked, pushed or otherwise tumbles to the ground. A research team from Switzerland’s ETH Zurich University trained ANYmal using reinforcement learning (RL) and published their work last Wednesday.
Reinforcement learning (RL) has been making spectacular achievements, e.g., Atari games, AlphaGo, AlphaGo Zero, AlphaZero, DeepStack, Libratus, OpenAI Five, Dactyl, DeepMimic, Catch The Flag, learning to dress, data center cooling, chemical syntheses, drug design, etc. See more RL applications.
The DeepMimic paper’s first author, Berkeley PhD student Xue Bin Peng, has now open-sourced the project’s codes, data, and frameworks. Moreover, Peng’s new research demonstrates that DeepMimic’s simulated characters can also learn to perform highly dynamic movements by using regular video clips of human examples as input data.
UC Berkeley researchers have published a paper demonstrating how Deep Reinforcement Learning can be used to control dexterous robot hands for complicated tasks. Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations proposes a low-cost and high-efficiency control method that uses demonstration and simulation techniques to accelerate the learning process.
Benjamin Sanchez-Lengeling from Harvard University and Alán Aspuru-Guzik from the University of Toronto have successfully applied machine learning models to speed up the materials discovery process. Their paper Inverse molecular design using machine learning: Generative models for matter engineering was published July 27 in Science Vol. 361.
Google has announced the release of MusicVAE, a machine learning model that makes composing musical scores as easy as mixing paint on a palette. A breakthrough from Google Brain’s Magenta Project, MusicVAE generates and morphs melodies to output multi-instrumental passages optimized for expression, realism and smoothness which sound convincingly like human-composed music.
To boost learning research aimed at endowing robots with better generalization capabilities, Yi Wu from UC Berkeley and Yuxin Wu, Georgia Gkioxari, and Yuandong Tian from Facebook AI research recently published the paper Building Generalizable Agents with a Realistic and Rich 3D Environment.