Applying reinforcement learning (RL) to combinatorial optimization problems is attractive as it removes the need for expert knowledge or pre-solved instances. However, it is unrealistic to expect an agent to solve these (often NP-)hard problems in a single shot at inference due to their inherent complexity. Thus, leading approaches often implement additional search strategies, from stochastic sampling and beam-search to explicit fine-tuning. In this paper, we argue for the benefits of learning a population of complementary policies, which can be simultaneously rolled out at inference. To this end, we introduce Poppy, a simple training procedure for populations. Instead of relying on a predefined or hand-crafted notion of diversity, Poppy induces an unsupervised specialization targeted solely at maximizing the performance of the population. We show that Poppy produces a set of complementary policies, and obtains state-of-the-art RL results on three popular NP-hard problems: traveling salesman, capacitated vehicle routing, and job-shop scheduling.

Applying reinforcement learning (RL) to combinatorial optimization problems is attractive as it removes the need for expert knowledge or pre-solved instances. However, it is unrealistic to expect an agent to solve these (often NP-)hard problems in a single shot at inference due to their inherent complexity. Thus, leading approaches often implement additional search strategies, from stochastic sampling and beam-search to explicit fine-tuning. In this paper, we argue for the benefits of learning a population of complementary policies, which can be simultaneously rolled out at inference. To this end, we introduce Poppy, a simple training procedure for populations. Instead of relying on a predefined or hand-crafted notion of diversity, Poppy induces an unsupervised specialization targeted solely at maximizing the performance of the population.

This ongoing debate of marketer vs machines seems to be a little skewed to me. The idea of machines, as we know it comes from our knowledge based on popular culture. Movies like 2001: A Space Odyssey, Westworld, Alien, etc. have shown us what machines and AI can do. Needless to say, the portrayal of machines in popular culture show what people think of them in reality. These serve as cautionary tales in case we actually start putting our faith in machines.

"Whenever you compete, you have to accept simple rules – someone wins, someone loses, and usually the winner takes it all." For this week's ML practitioner's series, Analytics India Magazine got in touch with Oleg Yaroshevskiy from Ukraine. In this interview, he shares his experiences from his journey to the top 20 in one of the toughest data science competitions in the world. Oleg majored in maths and statistics from Cybernetics Faculty of Taras Shevchenko National University of Kyiv, which was co-founded by Victor Glushkov, one of the cybernetics pioneers who played a key role in the advancement of theoretical computer science, including artificial intelligence. Oleg had a formal introduction to machine learning (ML) during his graduation days where he had studied neural networks along with the popular Andrew NG's course on Coursera back in 2013.

In the third decade of the commercial internet, concentration of power and money is greater than ever. Will this process stop or reverse? Or are we heading for a future of even stronger corporate dominance? Netopia talked to Jonathan Taplin, author of Move Fast and Break Things – a book which takes a closer look at the ideology and business of Silicon Valley's internet skyscrapers. Per Strömbäck: Is the "do first, ask later"-ideology the key to Silicon Valley's success?