Collaborating Authors

Reinforcement Learning

Robots learning to move like animals


Whether it's a dog chasing after a ball, or a monkey swinging through the trees, animals can effortlessly perform an incredibly rich repertoire of agile locomotion skills. But designing controllers that enable legged robots to replicate these agile behaviors can be a very challenging task. The superior agility seen in animals, as compared to robots, might lead one to wonder: can we create more agile robotic controllers with less effort by directly imitating animals? In this work, we present a framework for learning robotic locomotion skills by imitating animals. Given a reference motion clip recorded from an animal (e.g. a dog), our framework uses reinforcement learning to train a control policy that enables a robot to imitate the motion in the real world.

Curriculum for Reinforcement Learning


A curriculum is an efficient tool for humans to progressively learn from simple concepts to hard problems. It breaks down complex knowledge by providing a sequence of learning steps of increasing difficulty. In this post, we will examine how the idea of curriculum can help reinforcement learning models learn to solve complicated tasks. It sounds like an impossible task if we want to teach integral or derivative to a 3-year-old who does not even know basic arithmetics. That's why education is important, as it provides a systematic way to break down complex knowledge and a nice curriculum for teaching concepts from simple to hard. A curriculum makes learning difficult things easier and approachable for us humans.

Physically realistic attacks on deep reinforcement learning


Deep reinforcement learning (RL) has achieved superhuman performance in problems ranging from data center cooling to video games. RL policies may soon be widely deployed, with research underway in autonomous driving, negotiation and automated trading. Many potential applications are safety-critical: automated trading failures caused Knight Capital to lose USD 460M, while faulty autonomous vehicles have resulted in loss of life. Consequently, it is critical that RL policies are robust: both to naturally occurring distribution shift, and to malicious attacks by adversaries. Unfortunately, we find that RL policies which perform at a high-level in normal situations can harbor serious vulnerabilities which can be exploited by an adversary.

Now hiring AI futurists: It's time for artificial intelligence to take a seat in the C-Suite ZDNet


Machine learning, task automation and robotics are already widely used in business. These and other AI technologies are about to multiply, and we look at how organizations can best take advantage of them. COVID-19 disruption has left enterprises with no choice but to reassess digital transformation investments and roadmaps. While less important projects are delayed, transformation projects involving AI and automation are receiving a lot of attention right now. In just the last 60 days, the adoption of varying levels of AI technologies across the enterprise surged with an incredible sense of urgency.

What You Need to Know About Deep Reinforcement Learning - KDnuggets


It is useful, for the forthcoming discussion, to have a better understanding of some key terms used in RL. Agent: A software/hardware mechanism which takes certain action depending on its interaction with the surrounding environment; for example, a drone making a delivery, or Super Mario navigating a video game. The algorithm is the agent. Action: An action is one of all the possible moves the agent can make. An action is almost self-explanatory, but it should be noted that agents usually choose from a list of discrete possible actions.

Artificial Intelligence for Business


Online Courses Udemy Artificial Intelligence for Business, Solve Real World Business Problems with AI Solutions Created by Hadelin de Ponteves, Kirill Eremenko, SuperDataScience Team English [Auto-generated], French [Auto-generated], 5 more Students also bought Data Science: Natural Language Processing (NLP) in Python Deep Learning: Advanced Computer Vision (GANs, SSD, More!) Tensorflow 2.0: Deep Learning and Artificial Intelligence Machine Learning Practical: 6 Real-World Applications Artificial Intelligence: Reinforcement Learning in Python Preview this course GET COUPON CODE Description Structure of the course: Part 1 - Optimizing Business Processes Case Study: Optimizing the Flows in an E-Commerce Warehouse AI Solution: Q-Learning Part 2 - Minimizing Costs Case Study: Minimizing the Costs in Energy Consumption of a Data Center AI Solution: Deep Q-Learning Part 3 - Maximizing Revenues Case Study: Maximizing Revenue of an Online Retail Business AI Solution: Thompson Sampling Real World Business Applications: With Artificial Intelligence, you can do three main things for any business: Optimize Business Processes Minimize Costs Maximize Revenues We will show you exactly how to succeed these applications, through Real World Business case studies. And for each of these applications we will build a separate AI to solve the challenge. In Part 1 - Optimizing Processes, we will build an AI that will optimize the flows in an E-Commerce warehouse. In Part 2 - Minimizing Costs, we will build a more advanced AI that will minimize the costs in energy consumption of a data center by more than 50%! Just as Google did last year thanks to DeepMind.

AI and Machine Learning for Healthcare - KDnuggets


The 21st century is only two decades old and it is certain that one of the biggest transformative technologies and enablers for human society of this century is going to be Artificial intelligence (AI). It is a well-established idea that AI and associated services and platforms are set to transform global productivity, working patterns, and lifestyles and create enormous wealth. For example, McKinsey sees it delivering global economic activity of around $13 trillion by 2030. In the short-term, research firm Gartner expects the global AI-based economic activity to increase from about $1.2 trillion in 2018 to about $3.9 Trillion by 2022. It is no secret that this transformation is being, to a large extent, fueled by the powerful Machine Learning (ML) tools and techniques such as Deep Convolutional Networks, Generative Adversarial Networks (GAN), Gradient-boosted-tree models (GBM), Deep Reinforcement Learning (DRL), etc.

Artificial Intelligence Can Devise An Optimal Tax Policy To Reduce Inequality -- AI Daily - Artificial Intelligence News


Identifying the optimal level of taxation is quite complex. Human behaviour is highly unpredictable and gathering data can be time consuming. Despite decades of economic research being put into finding the optimal tax rate, it remains an open problem. But, scientists at the US business technology company, Salesforce, believe they may have found the key to solving the problem – Artificial Intelligence. The team has developed an AI system called the AI Economist, which uses reinforcement learning technology to identify the optimal level of taxation to make reduce inequality.

Google Brain's DRL Helps Robots 'Think While Moving' - Synced


When chasing a bouncing ball, a human will head where they anticipate the ball is going. If things change -- for example a cat swats the ball and it bounces off in a new direction -- the human will correct to an appropriate new route in real time. Robots can have a hard time making such changes, as they tend to simply observe states, then calculate and execute actions, rather than thinking while moving. Google Brain, UC Berkeley, and X Lab have proposed a concurrent Deep Reinforcement Learning (DRL) algorithm that 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. The paper has been accepted by ICLR 2020.