In this follow up post we apply the same methods we developed previously to a different dataset. In this third post we mix the previous two datasets. So, on the one hand, we have noise signals, on the other hand we have innovators and followers.
In this follow up post we apply the same methods we developed previously to a different dataset.
In this post we present the results of a competition between various forecasting techniques applied to multivariate time series. The forecasting techniques we use are some neural networks, and also – as a benchmark – arima. In particular the neural networks we considered are long short term memory (lstm) networks, and dense networks. The winner in the […]
Intro In this post we report success in using reinforcement to learn the game of nim. We had previously cited two theses (ERIK JÄRLEBERG (2011) and PAUL GRAHAM & WILLIAM LORD (2015)) that used Q-learning to learn the game of nim. However, in this setting, the scaling issues with Q-learning are much more severe than with value-learning. In […]
There are entire theses devoted to reinforcement learning of the game of nim, in particular those of ERIK JÄRLEBERG (2011) and PAUL GRAHAM & WILLIAM LORD (2015). Those two were successful in training a reinforcement-based agent to play the game of nim with a high percentage of accurate moves. However, they used lookup tables as their evaluation functions, which […]
This post starts a mini series of two posts in which we want to solve the Game of Nim using Reinforcement learning. The first part of this mini series is devoted to having a look at using our own Nim-specific custom environment for OpenAI. The Game of Nim is a simple two player game. The […]
Recap: Previously we constructed a very simple class to emulate the type of environment which is provided by OpenAI. Windy Walk (part 1) Then we implemented the same windy walk model as an extension to OpenAI. For this we created a custom python package, we named it gym_drifty_walk, you can grab it from github . These two versions […]
Recap: Previously we constructed a very simple class to emulate the type of environment which is provided by OpenAI. Then we simulated two windy walks and used the result of these walks to produce some plots. Now we want to produce the same results again but via a different and more interesting route. This time […]
So, today we advance to something slightly more interesting. OpenAI, founded by Elon Musk and Sam Altman, is a cool platform for testing artificial intelligence algorithms. The platform aims to provide a consistent interface for a host of different environments. It is also extensible. The most import thing in this mini-series of two posts is this: […]
This is a simple illustration that the code highlighting works plots are shown This post that was exported from a Jupyiter notbook, as described in the previous post Introduction and Hello! We start with importing numpy and matplotlib, two important python packages.
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.style as style
Now we generate vectorised x and y values for plotting:
X = np.array(range(200)) * np.pi/100
Y = np.sin(X)
So, it […]