Scaling our work to the real world can be messy and difficult. That’s where our Applied Research team comes in. They find ways to take research breakthroughs to the real world, and publish their findings to help others in the wider machine learning and engineering communities overcome similar challenges.
Find out more about some of our team’s research below:
Deep Reinforcement Learning in Large Discrete Action Spaces
Applying reasoning in an environment with a large number of discrete actions to bring reinforcement learning to a wider class of problems.
Deep Reinforcement Learning with Attention for Slate Markov Decision Processes with High-Dimensional States and Actions
Introducing slate Markov Decision Processes (MDPs), a formulation that allows reinforcement learning to be applied to recommender system problems.
Massively Parallel Methods for Deep Reinforcement Learning
Presenting the first massively distributed architecture for deep reinforcement learning.
Adaptive Lambda Least-Squares Temporal Difference Learning
Learning to select the best value of λ (which controls the timescale of updates) for TD(λ) to ensure the best result when trading off bias against variance.
Learning from Demonstrations for Real World Reinforcement Learning
Presenting Deep Q-learning from Demonstrations (DQfD), an algorithm that leverages data from previous control of a system to accelerate learning.
Value-Decomposition Networks For Cooperative Multi-Agent Learning
Studying the problem of cooperative multi-agent reinforcement learning with a single joint reward signal.
Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
Demonstrating an alternative view of the training of GANs.
Risk-Constrained Reinforcement Learning with Percentile Risk Criteria
Presenting efficient reinforcement learning algorithms for risk-constrained Markov decision processes (MDPs) and demonstrating their effectiveness in an optimal stopping problem and an online marketing application.