Bonsai was built on the core belief that the best way for machines to learn is to teach them. Just like we teach humans to solve problems, so can we teach machines using the expertise we already have. …

This is the second post in our Simulation and Deep Reinforcement Learning (DRL) series. In our first post, we covered the benefits of simulations as training environments for DRL. Now, we’ll focus on how to to make simulations + DRL work. In the example below, we will train a Bonsai…

Deep reinforcement learning (DRL) is one of the most exciting fields in AI right now. …

Deep reinforcement learning has generated tons of buzz for its ability to beat games like AlphaGo and Poker. But the technology has advanced to the point of being able to solve real business problems across industries like manufacturing, supply chain and energy optimization. Watch Bonsai’s Kence Anderson and Redmonk co-founder and analyst, Stephen O’Grady, give a brief overview of deep reinforcement learning, simulations and how enterprises can apply deep reinforcement learning to automate and optimize their own real-world business problems. Kence also demonstrates how the Bonsai Platform uses deep reinforcement learning to optimize the energy of a wind farm.

In this post, I’m going to cover tricks and best practices for how to write the most effective reward functions for reinforcement learning models. If you’re unfamiliar with deep reinforcement learning, you can learn more about it here before jumping into the post below. The Cobra Effect Crafting reward functions for reinforcement learning…

TensorFlow is unquestionably a powerful tool for training AI models and a crucial part of the emerging AI ecosystem. …

Most of the chatter around AI focuses on problems such as data analysis (data mining, customer segmentation), prediction (churn prediction, fraud detection, product recommendation) and perception (facial recognition, language translation, identifying birds). Typically, those kinds of AI problems are finite, constrained and relatively low in risk. Nobody dies if you…

One of the first things to know about machine learning is that you will be working with one of three types of algorithms: supervised learning, unsupervised learning and reinforcement learning. Here’s a quick summary of the three types: Supervised learning — You’re feeding labeled data into a neural network. …

Reinforcement learning is an increasingly popular machine learning technique that is particularly well suited for addressing problems within dynamic and adaptive environments. …