reinforcement learning

Top Indian University-Industry Partnerships For AI In 2021

The following is a list of the leading research laboratories in Indian institutions that are advancing and innovating in artificial intelligence.

Top Books On AI Released In 2021

Want to learn more about AI/ML this year? Check out these great books on AI fundamentals and applications.

An Introductory Guide to Meta Reinforcement Learning (Meta-RL)

Meta Reinforcement learning(Meta-RL) can be explained as performing meta-learning in the field of reinforcement learning. where including meta-learning models in reinforcement learning we can grow the model to perform a variety of tasks.

What Happened in Reinforcement Learning in 2021

2021 saw innovations in the reinforcement learning space in the robotics, gaming , sequential decision making space amidst growing curiosity among students and professionals.

AI Good Teammate
Can AI Be A Good Teammate?

Recently, researchers have been able to develop a few RL agents that can learn games from scratch through pure self-play without any human input.

Facebook Wants To Make Reinforcement Learning Easier

A versatile and simple library for sequential agent learning, including reinforcement learning

All Hail The King of Reinforcement Learning, DeepMind
All Hail The King of Reinforcement Learning, DeepMind

Besides reinforcement learning, DeepMind also looks at other fundamental areas like symbolic AI and population-based training.

Can A Robot Be Used To Locate Misplaced Items?

MIT researchers have developed a robotic system capable of sorting through clutter to locate an object.

BERT in Google Search
Google AI Introduces Pathdreamer, A World Model for Indoor Navigation

Pathdreamer is an indoor navigation world model that generates high-resolution 360ยบ visual observations of areas of a building unseen by an agent.

Big Tech & Their Favourite Deep Learning Techniques
Big Tech & Their Favourite Deep Learning Techniques

For instance, Facebook AI Research (FAIR) has been championing self-supervised learning (SSL) for quite some time.

Imitation Learning Bodes A New Milestone In Robotics

Generic imitation learning systems could aid in the tough challenge of teaching a robot to perform a task.

In Conversation With AI Scientist Dr Ganapathi Pulipaka On Gallium Nitride Processors For Future Space Exploration
In Conversation With AI Scientist Dr Ganapathi Pulipaka On Gallium Nitride Processors For Future Space Exploration

AIM interviews Dr Ganapathi Pulipaka on gallium nitride processors for future space exploration, deep quest of AI, deep learning algorithms, reinforcement learning and high-performance computing.