Archives: Research Blog

Articles

Exact Combinatorial Optimisation with Deep Reinforcement Learning

A blog post covering our recent publication: Christopher W. F. Parsonson, Alexandre Laterre, and Thomas D. Barrett, ‘Reinforcement Learning for Branch-and-Bound Optimisation using Retrospective Trajectories’, AAAI’23: Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023  Branch-and-bound solvers for combinatorial optimisation Formally, ‘combinatorial optimisation’ (CO) problems consider the task of assigning integer values to a… Read more »

Population-Based Reinforcement Learning for Combinatorial Optimization

Continuing the innovation and application of machine learning to the hardest and most impactful challenges, InstaDeep is pleased to share its new breakthrough on applying reinforcement learning to complex combinatorial problems.  Our new work, “Population-Based Reinforcement Learning for Combinatorial Optimization” introduces a new framework for learning a diverse set of complementary agents, and obtains state-of-the-art… Read more »

Autoregressive neural-network wavefunctions for ab initio quantum chemistry

InstaDeep is delighted to announce that a collaborative research project with a team from the University of Oxford on “Autoregressive neural-network wavefunctions for ab initio quantum chemistry” has been published in Nature Machine Intelligence magazine.   The paper was authored by Dr Thomas Barrett of InstaDeep as well as Prof A. I. Lvovsky and Aleksei Malyshev… Read more »

Model Agnostic Meta-Learning made simple

(Part 2/4) In our introduction to meta-reinforcement learning, we presented the main concepts of meta-RL: Meta-Environments are associated with a distribution of distinct MDPs called tasks. The goal of Meta-RL is to learn to leverage prior experience to adapt quickly to new tasks. In Meta-RL, we learn an algorithm during a step called meta-training. At meta-testing, we apply this… Read more »

A simple introduction to Meta-Reinforcement Learning

(Part 1/4) The recent developments in Reinforcement Learning (RL) have shown the incredible capacity of computers to outperform human performance in many environments such as Atari Games [1], Go, chess, shogi [2], Starcraft II [3]. This performance results from the development of Deep Learning and Reinforcement Learning methods like Deep Q-Networks (DQN) [4] and actor-critic methods [5, 6, 7, 8]. However, one essential advantage of… Read more »