Preferred Networks’ ChainerRL Joins PyTorch Ecosystem as ‘PFRL’
Japanese AI startup Preferred Networks (PFN) is moving ChainerRL to the PyTorch ecosystem.
Tag: Reinforcement Learning
UC Berkeley Reward-Free RL Beats SOTA Reward-Based RL
Augmented Temporal Contrast (ATC), a new unsupervised learning (UL) task for learning visual representations agnostic to rewards and without degrading the control policy.
Salesforce’s AI-Powered Economist Seeks to Optimize Income Equality and Productivity
The AI Economist uses a two-level RL framework where a collection of AI agents simulate how humans might react to various taxes in a principled economic simulation.
Using Deep RL to Model Human Locomotion Control in Neuromechanical Simulations
Researchers from Stanford University, UC Berkeley and CMU review neuromechanical simulations and DRL, with a focus on modelling the control of human locomotion.
DeepMind & McGill Employ Operations Generalization to Divide & Conquer Complex RL Problems
DeepMind and McGill University researchers believe the problem could be solved through a strategic “divide-and-conquer” approach.
DeepMind & Google Explore Hyperparameter Selection for Offline RL
Researchers conducted a thorough empirical study of hyperparameter selection for offline RL, aiming to identify and develop more reliable and effective approaches.
Preferred Networks Releases PFRL Deep Reinforcement Learning Library for PyTorch Users
PFRL succeeds ChainerRL as comprehensive library with cutting-edge deep reinforcement learning algorithms and features.
Introducing TayPO, a Unifying Framework for Reinforcement Learning
Researchers proposed a Taylor Expansion Policy Optimization (TayPO) framework that combines two leading algorithmic improvement methods.
DeepMind Explores Deep RL for Brain and Behaviour Research
DeepMind researchers call attention to another “fundamentally novel” development in AI research — deep reinforcement learning (deep RL) — which they believe also has vital implications for neuroscience and deserves more attention from neuroscientists.
NetHack: Fast & Complex Learning Environment For Testing RL Agent Robustness & Generalization
NLE is a procedurally generated environment for testing the robustness and systematic generalization of RL agents.
Reimagining the Dog: New DeepMind Models and Tutorial for Physics-Based RL Tasks
DeepMind researchers released several new models and a tutorial for their dm_control software stack for physics-based simulation and reinforcement learning environments using MuJoCo physics.
Toward Practical Real-World RL: New Criterion & Algorithm Enhance Deployment Efficiency
Researchers from the University of Tokyo and Google Research have proposed a new metric for RL performance and novel BREMEN algorithm designed to manage the costs and risks of new policy deployment.
DeepMind Introduces ‘Acme’ Research Framework for Distributed RL
DeepMind researchers introduce a framework that aims to solve the problem by enabling simple RL agent implementations to be run at different scales of execution.
Self-Supervised ‘Plan2Explore’ RL Agent Achieves SOTA Zero-Shot and Adaptation Performance
Enter Plan2Explore — a self-supervised RL agent designed to quickly generalize to unseen tasks in a zero or few-shot manner.
Google Brain’s DRL Helps Robots ‘Think While Moving’
The proposed concurrent DRL algorithm enables robots to take a broader and more long-term view of tasks and behaviours, and decide on their next action before the current one is completed.
Google DeepMind ‘Agent 57’ Beats Human Baselines Across Atari Games Suite
Agent57 is the first deep reinforcement learning (RL) agent to top human baseline scores on all games in the Atari57 test set.
Google Introduces Neuroevolution for Self-Interpretable Agents
Researchers from Google Brain Tokyo and Google Japan have proposed a novel approach that helps guide reinforcement learning (RL) agents to what’s important in vision-based tasks.
DeepMind Releases New JAX Libraries for Neural Networks and Reinforcement Learning
DeepMind announced yesterday the release of Haiku and RLax — new JAX libraries designed for neural networks and reinforcement learning respectively.
SLM Lab: New RL Research Benchmark & Software Framework
In an effort to sustain RL’s momentum, a team of researchers from Machine Zone, Google Brain, and California Institute of Technology have introduced a new software framework and benchmark for reproducible reinforcement learning research.
Playing Space Invaders Blind | RL & Cross Modality Transfer
Using cross-modality transfer techniques and reinforcement learning (RL), the researchers produced an agent that can play video games with only the game audio to guide it.
DeepMind Research Lead Doina Precup On Reinforcement Learning
Precup discussed the latest developments in the field: “Reinforcement learning allows autonomous agents to learn how to act in a stochastic, unknown environment, with which they can interact.”
Texas A&M and Simon Fraser Universities Open-Source RL Toolkit for Card Games
A team of researchers from Texas A&M University and Canada’s Simon Fraser University have open-sourced a toolkit called “RLCard” for applying RL research to card games.
Robots to Handle Rubik’s Cube, Push Stuff Around, Build a Lunar Base
Synced Global AI Weekly October 20th
RE•WORK AI in Finance | Federated AI, Reinforcement Learning and BERT
At last week’s Re•Work AI in Finance Conference in New York, researchers and engineers from banks and academia alike shared their thoughts on current AI research and applications in the finance world.
Why Playing Hide-and-Seek Could Lead AI to Humanlike Intelligence
A new paper from San Francisco-based OpenAI proposes training models in the children’s game of hide-and-seek and pitting them against each other.
DeepMind ‘Bsuite’ Evaluates Reinforcement Learning Agents
Now AI researchers have created a similar evaluation system to assess the relative performance of reinforcement learning (RL) systems across different tasks.
DeepMind Transporter: Unsupervised Learning of Object Keypoints
In common reinforcement learning (RL) domains, existing keypoint discovery methods struggle to perceive keypoints in an image when there are limited objects present.
AI Development and Trends in E-Commerce
The traditional retail industry is undergoing a significant reinvention and upgrade as more and more brick and mortar stores boost business by adopting e-commerce platforms powered by cutting-edge tech.
UC Berkeley’s RL-Powered SOLAR Accelerates Robotic Learning
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.
NeurIPS 2019 Will Host Minecraft Reinforcement Learning Competition
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”.
Improving Robot Control With Residual RL
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.
Google Brain SimPLe: Complete Model-Based Reinforcement Learning for Atari
Model-free reinforcement learning can be used to learn effective strategies for complex tasks such as Atari games, but it usually requires a large amount of interaction, which adds significant time and cost.
Triple ‘Strong Accept’ for CVPR 2019: Reinforced Cross-Modal Matching & Self-Supervised Imitation Learning for Vision-Language Navigation
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.
After Mastering Go and StarCraft, DeepMind Takes on Soccer
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.”
Yann LeCun Cake Analogy 2.0
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 Open-Sources Improved Go Bot and Huge Game Library
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’s Go-Explore Tackles Hard-Exploration Problems
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.
You Can’t Keep an RL-Powered ANYmal Down
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.
Explore, Exploit, and Explode — The Time for Reinforcement Learning is Coming
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.
Global Companies Are Making AI Breakthroughs
Synced Global AI Weekly November 25th