Anurag Upadhyaya

Product Manager, Data Science

7 Articles0 Comments

Experienced Data Scientist with a demonstrated history of working in Industrial IOT (IIOT), Industry 4.0, Power Systems and Manufacturing domain. I have experience in designing robust solutions for various clients using Machine Learning, Artificial Intelligence, and Deep Learning. I have been instrumental in developing end to end solutions from scratch and deploying them independently at scale.

Hands-On Guide to Understand and Implement Q-Learning

Q-Learning is a traditional model-free approach to train Reinforcement Learning agents. It is also viewed as a method of asynchronous dynamic programming. It was introduced by Watkins&Dayan in 1992. Overview In Q-Learning we build a Q-Table to store Q values…

Hands-On Guide to OpenAI Gym Custom Environments

enAI Gym is a well known RL community for developing and comparing Reinforcement Learning agents. OpenAI Gym doesn’t make assumptions about the structure of the agent and works out well with any numerical computation library such as TensorFlow, PyTorch.

A Hands-On Guide on Training RL Agents on Classic Control Theory Problems

Various Benchmarks have played an important role in various domains of machine learning such as MNIST (LeCun et al., 1998), Caltech101 (Fei-Fei et al., 2006), CIFAR (Krizhevsky & Hinton, 2009), ImageNet (Deng et al., 2009). However, there is a lack…

Vision, Control, Planning, and Generalization in RL

In the last two articles, the focus has been to measure the generalization performance of Reinforcement learning agents using Gym Retro and Procgen environments.  Both these environments used 2-D environments and were limited to the first player arcade gaming experience.…

Generalization in Reinforcement Learning – Exploration vs Exploitation

In Reinforcement learning, the generalization of the agents is benchmarked on the environments they have been trained on. In a supervised learning setting, this would mean testing the model using the training dataset. OpenAI has open-sourced Procgen-benchmark emphasizing the generalization…

Hands-On Guide To Train RL Agents using Stable BaseLines on Atari Gym Environment

Reinforcement learning is continuously being made easy by OpenAI. On their, mission to develop and promote friendly AI that helps humanity, OpenAI released Stable-Baselines. It was created by Robotics Lab U2IS (INRIA Flowers Team) at ENSTA Paris with a goal…

Hands-on Guide To Creating RL Agents Using OpenAI Gym Retro

The goal of any Reinforcement learning agent is to maximize the cumulative rewards based on the goals for the provided environment. The learner is not told which actions to take but must discover which actions yield the most rewards by…

More than 1,00,000 people are subscribed to our newsletter

Subscribe now to receive in-depth stories on AI & Machine Learning.