InfoQ Homepage Reinforcement Learning Content on InfoQ
News
RSS Feed-
Meta Optimizes Data Center Sustainability with Reinforcement Learning
In a recent blog post, Meta describes how its engineers use reinforcement learning (RL), to optimize environmental controls in Meta’s data centers, reducing energy consumption and water usage while addressing broader challenges such as climate change.
-
NVIDIA Open-Sources Robot Learning Framework Orbit
A team of researchers from NVIDIA, ETH Zurich, and the University of Toronto open-sourced Orbit, a simulation-based robot learning framework. Orbit includes wrappers for four learning libraries, a suite of benchmark tasks, and simulation for several robot platforms, as well as interfaces for deploying trained agents on physical robots.
-
Netflix’s New Algorithm Offers Optimal Recommendation Lists for Users with Finite Time Budget
Netflix developed a new machine learning algorithm based on reinforcement learning to create an optimal list of recommendations considering a finite time budget for the user. In a recommendation use case, often the factor of finite time to make a decision is ignored.
-
PrefixRL: Nvidia's Deep-Reinforcement-Learning Approach to Design Better Circuits
Nvidia has developed PrefixRL, an approach based on reinforcement learning (RL) to designing parallel-prefix circuits that are smaller and faster than those designed by state-of-the-art electronic-design-automation (EDA) tools.
-
OpenAI Releases Minecraft-Playing AI VPT
Researchers from OpenAI have open-sourced Video PreTraining (VPT), a semi-supervised learning technique for training game-playing agents. In a zero-shot setting, VPT performs tasks that agents cannot learn via reinforcement learning (RL) alone, and with fine-tuning is the first AI to craft a diamond pickaxe in Minecraft.
-
DeepMind Trains AI Controller for Nuclear Fusion Research Device
Researchers at Google subsidiary DeepMind and the Swiss Plasma Center at EPFL have developed a deep reinforcement learning (RL) AI that creates control algorithms for tokamak devices used in nuclear fusion research. The system learned control policies while interacting with a simulator, and when used to control a real device was able to achieve novel plasma configurations.
-
Allen Institute Launches Updated Embodied AI Challenge
The Allen Institute for AI (AI2) has announced the 2022 version of their AI2-THOR Rearrangement Challenge. The challenge requires competitors to design an autonomous agent that can move objects in a virtual room and includes several improvements including a new dataset and faster training using the latest release of the AI2-THOR simulation platform.
-
University Researchers Develop Brain-Computer Interface for Robot Control
Researchers from École Polytechnique Fédérale de Lausanne (EPFL) in Switzerland and the University of Texas at Austin (UT) have developed a brain-computer interface (BCI) that allows users to modify a robot manipulator's motion trajectories. The system uses inverse reinforcement learning (IRL) and can learn a user's preferences using less than five demonstrations.
-
Joanneum Research Releases Robot AI Platform Robo-Gym Version 1.0.0
Joanneum Research's Institute for Robotics and Mechatronics has released version 1.0.0 of robo-gym, an open-source framework for developing reinforcement learning (RL) AI for robot control. The release includes a new obstacle avoidance environment, support for all Universal Robots cobot models, and improved code quality.
-
DeepMind's Agent57 Outperforms Humans on All Atari 2600 Games
Researchers at Google's DeepMind have produced a reinforcement-learning (RL) system called Agent57 that has scored above the human benchmark on all 57 Atari 2600 games in the Arcade Learning Environment. Agent57 is the first system to outperform humans on even the hardest games in the suite.