In the previous blog, we discussed a simple armed bandit problem, in this blog, we’ll discuss the multi-armed Bandit problem. In the previous example, we did not consider the states of the bandit and we relied only on action. In this blog, we’ll try to solve the problem which neither fully RL problem or fully…
Read more
In the previous blogs, we discussed Reinforcement Learning, in this blog we will try to solve the Multi-Armed Bandit Problem using reinforcement learning technique. Multi-armed Bandit problem is classic RL problem and it check the allocation of resource the maximize the gain. Our goal for the multi-armed bandit problem is to have a such strategy…
Read more
In the previous blog, we discussed the REINFORCE algorithm, in this blog we’ll discuss Markov Decision Process. This will help us to understand other algorithms where Gradient Policy algorithm itself try to optimize the policy to maximize the reward. Markov Chain Markov process is named after the Russian Mathematician Andrey Markov. It is a stochastic process that…
Read more
In the previous blog, we discussed the Neural Network based policy, in this blog we are going to discuss the RL Policy Gradient. When we are playing a game like Frozen Lake in the previous blog, we may reach the goal but before reaching the goal, there may be various steps involved which result in…
Read more
In the previous blog, we created a simple example of reinforcement learning using a simple policy, in this blog, we’ll use a neural network to decide the action. Since the frozen lake was having a shape of 4*4 that means the agent can be at one space at any time. That means out input will…
Read more
In the previous few blogs, we discussed Autoencoders, now we’ll start working on Reinforcement Learning. As per Wikipedia, Reinforcement Learning is : An area of machine learning concerned with how software agents ought to take actions in an environment so as to maximize some notion of cumulative reward Wikipedia Reinforcement Learning falls in between the supervise learning (where we have labeled data) and unsupervised…
Read more
In the previous few blogs, we talked about Autoencoder, in this blog we’ll discuss Denoising Autoencoder. As we know that one of the challenges of the Autoencoder to make sure that it is just not only copy the input as an output. One of the ways to achieve this is by forcing Autoencoder to add…
Read more
In the previous blog, we discussed Sparse Autoencoder, in this blog we’ll discuss the Variational Autoencoder. Variational Autoencoder is different from the other Autoencoder which we have discussed in past. This was first introduced in 2014 “Auto-Encoding Variational Bayes” by Diederik P. Kingma and Max Welling. These types of Autoencoders are different: These are probabilistic…
Read more
In the previous two blogs, we discussed under-complete autoencoder and deep autoencoder, in this blog we’ll discuss sparse autoencoder. Instead of controlling the number of hidden layer or dimension of encoder-decoder, we can use the loss functions which not only copy the input to output but also learn other representation of the input data. There…
Read more
In the previous blog, we discussed the simple Autoencoder, in this blog we’ll discuss Deep Autoencoder. Like Deep neural network, we can have more than one hidden layer for the Autoencoder. This kind of architecture called Deep Autoencoder / Stacked Autoencoder/ Multilayer Autoencoder. You don’t want to have multiple layers else Autoencoder may generalize the…
Read more