Goto

Collaborating Authors

Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning

Neural Information Processing Systems

The mutual information is a core statistical quantity that has applications in all areas of machine learning, whether this is in training of density models over multiple data modalities, in maximising the efficiency of noisy transmission channels, or when learning behaviour policies for exploration by artificial agents. Most learning algorithms that involve optimisation of the mutual information rely on the Blahut-Arimoto algorithm --- an enumerative algorithm with exponential complexity that is not suitable for modern machine learning applications. This paper provides a new approach for scalable optimisation of the mutual information by merging techniques from variational inference and deep learning. We develop our approach by focusing on the problem of intrinsically-motivated learning, where the mutual information forms the definition of a well-known internal drive known as empowerment. Using a variational lower bound on the mutual information, combined with convolutional networks for handling visual input streams, we develop a stochastic optimisation algorithm that allows for scalable information maximisation and empowerment-based reasoning directly from pixels to actions.


Robust Metric Learning by Smooth Optimization

arXiv.org Machine Learning

Most existing distance metric learning methods assume perfect side information that is usually given in pairwise or triplet constraints. Instead, in many real-world applications, the constraints are derived from side information, such as users' implicit feedbacks and citations among articles. As a result, these constraints are usually noisy and contain many mistakes. In this work, we aim to learn a distance metric from noisy constraints by robust optimization in a worst-case scenario, to which we refer as robust metric learning. We formulate the learning task initially as a combinatorial optimization problem, and show that it can be elegantly transformed to a convex programming problem. We present an efficient learning algorithm based on smooth optimization [7]. It has a worst-case convergence rate of O(1/{\surd}{\varepsilon}) for smooth optimization problems, where {\varepsilon} is the desired error of the approximate solution. Finally, our empirical study with UCI data sets demonstrate the effectiveness of the proposed method in comparison to state-of-the-art methods.


Want to Know More About Machine Learning and AI?

#artificialintelligence

Wondering whether you should invest in AI and Machine Learning? That's a question that the most innovative companies are considering. One good reason is because your competitors have already started. If that doesn't give you some reason to get motivated, I hope you get started before you are put out of business. To make sure that doesn't happen, there are a few things to consider to help you start to explore an investment in machine learning.


Robust Deep Reinforcement Learning via Multi-View Information Bottleneck

arXiv.org Artificial Intelligence

Deep reinforcement learning (DRL) agents are often sensitive to visual changes that were unseen in their training environments. To address this problem, we introduce a robust representation learning approach for RL. We introduce an auxiliary objective based on the multi-view information bottleneck (MIB) principle which encourages learning representations that are both predictive of the future and less sensitive to task-irrelevant distractions. This enables us to train high-performance policies that are robust to visual distractions and can generalize to unseen environments. We demonstrate that our approach can achieve SOTA performance on challenging visual control tasks, even when the background is replaced with natural videos. In addition, we show that our approach outperforms well-established baselines on generalization to unseen environments using the large-scale Procgen benchmark.


Future of Artificial Intelligence and Machine Learning

#artificialintelligence

Machine Learning and Artificial Intelligence are the "Buzz topics" in every trending article of 2021, and rightfully so. It is much like how the internet emerged as a game-changer in everyone's lifestyle, Artificial Intelligence and Machine Learning are poised to transform our lives which were unimaginable years ago. Artificial Intelligence (A.I.) is a simplified problem-solving process for humans. It empowers software to do jobs without being explicitly programmed. Also, it has neural networks and profound learning.