Between 9 and 15 March, 2016, the second-highest ranked Go player, Lee Sidol, took on a computer program named AlphaGo. AlphaGo emphatically outplayed and outclassed Mr. Sidol and won the series 4-1. Designed by Google's DeepMind, the program has spawned many other developments in AI, including AlphaGo Zero. These breakthroughs are widely considered as stepping stones towards Artificial General Intelligence (AGI). In this article, I will introduce you to the algorithm at the heart of AlphaGo – Monte Carlo Tree Search (MCTS). This algorithm has one main purpose – given the state of a game, choose the most promising move.

The internet is filled with tutorials to get started with Deep Learning. You can choose to get started with the superb Stanford courses CS221 or CS224, Fast AI courses or Deep Learning AI courses if you are an absolute beginner. All except Deep Learning AI are free and accessible from the comfort of your home. All you need is a good computer (preferably with a Nvidia GPU) and you are good to take your first steps into Deep Learning. This blog is however not addressing the absolute beginner.

Last month, Filestack sponsored an AI meetup wherein I presented a brief introduction to reinforcement learning and evolutionary strategies. Beforehand, I had promised code examples showing how to beat Atari games using PyTorch. In reality, I did not have time for that kind of side project and so I found some other examples of training agents to play Flappy Bird using Keras, which were entertaining but not complete enough for me to recommend as a springboard for further exploration. Luckily, I recently found some time to develop the promised training scripts. Therefore, I would like to provide an in-depth look of how we can use the PyTorch-ES suite for training reinforcement agents in a variety of environments, including Atari games and OpenAI Gym simulations. In deep reinforcement learning that uses the Q-learning algorithm, which has become very popular, training an intelligent agent includes distinct phases for "observation" and "learning".

This quote simply explains the complexity of Human Brain, Human brain is made up of billions of thinking units called Neurons, a single Neuron in brain is connected to several other Neurons through links just like electrical wires known as Axon, these axons provide a path for electrical impulses to move between individual neurons and thus knowledge moves on the form of electrical impulses in our brain. As many of you know Artificial intelligence is one of the hottest areas of research these days, it mainly deals with creation of man-made intelligent systems. We, Human beings are intelligent because we have the ability to gain knowledge, which forms core part of intelligence, practically it's very difficult for computers to gain knowledge because they are just made out of sand (Silicon), but how can they learn and gain knowledge? How can they become intelligent? How can they gain potential to influence our everyday life in the near future?

Artificial intelligence has been in the background for decades, kicking up dust in the distance, but never quite arriving. Well that era is over. In 2017, AI has broken through the dust cloud and arrived in a big way. And what do recurrent neural networks have to do with it? Thanks to an ingenious form of short-term memory that is unheard of in conventional neural networks, today's recurrent neural networks (RNNs) have been proving themselves as powerful predictive engines.