9 Best Articles in 2021
OpenAI
Reinforcement Learning with Prediction-Based Rewards
OpenAI
7 min read · 60 saves · From 2018 · We’ve developed Random Network Distillation (RND), a prediction-based method for encouraging reinforcement learning agents to explore their environments through curiosity, which for the first time exceeds average human performance on Montezuma’s Revenge.
nervanasys.com
Guest Post (Part I): Demystifying Deep Reinforcement Learning
nervanasys.com
~12 min read · 40 saves · From 2016 · This blog was first published at: http://neuro.cs.ut.ee/demystifying-deep-reinforcement-learning/ This is the part 1 of my series on deep reinforcement learning. Tune in next week for “Deep Reinforcement Learning with Neon” for an actual implementation with Neon deep learning toolkit.
VentureBeat
Google releases open source reinforcement learning framework for training AI models
VentureBeat
2 min read · 72 saves · From 2018 · Kyle Wiggers · Google's releasing a reinforcement learning framework that makes it easier to train AI models with cutting-edge techniques.
In Open Source
Towards Data Science
DeepMind Has Quietly Open Sourced Three New Impressive Reinforcement Learning Frameworks
Towards Data Science
5 min read · 93 saves · 2019-09-16 · Jesus Rodriguez · Three new releases that will help researchers streamline the implementation of reinforcement learning programs
thegradient.pub
Reinforcement learning’s foundational flaw
thegradient.pub
~14 min read · 60 saves · From 2018 · By definition, learning from scratch is just about the least sample-efficient approach there can be.
OpenAI
Evolution Strategies as a Scalable Alternative to Reinforcement Learning
OpenAI
10 min read · 65 saves · From 2017 · We've discovered that evolution strategies (ES), an optimization technique that's been known for decades, rivals the performance of standard reinforcement learning (RL) techniques on modern RL benchmarks (e.g. Atari/MuJoCo), while overcoming many of RL's inconveniences. In particular, ES is simpler to implement (there is no need for backpropagation)
alexirpan.com
Deep Reinforcement Learning Doesn't Work Yet
alexirpan.com
102 saves · From 2018 · June 24, 2018 note: If you want to cite an example from the post, please cite the paper which that example came from. If you want to cite the post as a whole, you can use the following BibTeX:
github.com
GitHub - janhuenermann/neurojs: A javascript deep learning and reinforcement learning library.
github.com
26 saves · From 2017 · neurojs - A javascript deep learning and reinforcement learning library.
Data Science Central
Introduction to Various Reinforcement Learning Algorithms
Data Science Central
2 min read · 25 saves · 2019-09-12 · Andrea Manero-Bastin on September 9, 2019 at 12:30am
View Blog · This article was written by Steeve Huang. Reinforcement Learning (RL) refers to a kind of Machine Learning method in which the agent receives a delayed rewar…
Trending
In Brain
Towards Data Science
Reinforcement Learning Explained Visually (Part 4): Q Learning, step-by-step
Towards Data Science
20+ min read · 88 saves · 2020-11-28 · Ketan Doshi · A Visual Guide to how and why the Q Learning Algorithm works, in Plain English
Nature
Autonomous balloons take flight with artificial intelligence
Nature
5 min read · 35 saves · 2020-12-02 · Scott M. Osprey · A real-world application of reinforcement learning.
In Microsoft
blogs.microsoft.com
With reinforcement learning, Microsoft brings a new class of AI solutions to customers
blogs.microsoft.com
4 min read · 16 saves · 2020-12-07 · Personalizer, the first Azure Cognitive Service to be built on reinforcement learning, grew out of a close collaboration between Microsoft researchers and Azure product experts. They wanted to help…
Forbes
The AI-Powered Robot That Learnt Curling Using Adaptive Deep Reinforcement Learning
Forbes
2 min read · 10 saves · Jan 11th · Using adaptive reinforcement learning, an AI-powered robot named Curly was able to beat human competitors in three out of four curling matches, a sport that requires strategy and precision. While…
More like this
Insight Data Science
Reinforcement Learning from scratch
Insight Data Science
~11 min read · 119 saves · From 2018 · Inspired by a great tutorial at O’Reilly AI
amid.fish
Lessons Learned Reproducing a Deep Reinforcement Learning Paper
amid.fish
~20 min read · 28 saves · From 2018 · There are a lot of neat things going on in deep reinforcement learning. One of the coolest things from last year was OpenAI and DeepMind’s work on training an agent using feedback from a human rather…
lilianweng.github.io
A (Long) Peek into Reinforcement Learning
lilianweng.github.io
20+ min read · 23 saves · From 2018 · In this post, we are gonna briefly go over the field of Reinforcement Learning (RL), from fundamental concepts to classic algorithms. Hopefully, this review is helpful enough so that newbies would not…
wildml.com
Learning Reinforcement Learning (with Code, Exercises and Solutions)
wildml.com
2 min read · 35 saves · From 2016 · Skip all the talk and go directly to the Github Repo with code and exercises. Why Study Reinforcement Learning Reinforcement Learning is one of the fields I’m most excited about. Over the pas…
github.com
dennybritz/reinforcement-learning: Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book…
github.com
25 saves · From 2016 · reinforcement-learning - Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.
Towards Data Science
New Game Theory Innovations that are Influencing Reinforcement Learning
Towards Data Science
5 min read · 44 saves · 2019-11-07 · Jesus Rodriguez · Game theory plays a fundamental factor in modern artificial intelligence(AI) solutions. Specifically, deep reinforcement learning(DRL) is…
analyticsvidhya.com
Beginner's guide to Reinforcement Learning & its implementation in Python
analyticsvidhya.com
~20 min read · 18 saves · From 2017 · This guide is an introduction to reinforcement learning & its practical implementations. It explains problem formulation, Q learning & a few examples of RL
Google AI
Introducing Google Research Football: A Novel Reinforcement Learning Environment
Google AI
4 min read · 29 saves · 2019-06-07 · Posted by Karol Kurach, Research Lead and Olivier Bachem, Research Scientist, Google Research, Zürich The goal of reinforcement learning...
In Economy
MIT Technology Review
An AI can simulate an economy millions of times to create fairer tax policy
MIT Technology Review
3 min read · 312 saves · 2020-05-05 · Deep reinforcement learning has trained AIs to beat humans at complex games like Go and StarCraft. Could it also do a better job at running the economy?