Title
Data-efficient Reinforcement Learning

CoPED ID
feb2fcf8-6514-44c3-8cc0-8a7e45a97e6f

Status
Closed


Value
No funds listed.

Start Date
Sept. 30, 2017

End Date
Sept. 30, 2020

Description

More Like This


Reinforcement Learning (RL) algorithms are an alternative to traditional model-based control that learn from data the optimal actions to take. Unlike the latter, RL methods do not need an in-built model of their dynamical system, enabling them to successfully make decisions when the true model is complicated or not perfectly known during design. Unfortunately, their application to many settings, such as autonomous robotics and smart buildings, is hampered by their need for large amounts of data. This project focuses on improving the data-efficiency of RL systems, using Bayesian inference and reasoning techniques similar to those from chess-playing AI. We will study systems that take into account the long-term value of a certain decision, both in terms of the benefits it achieves and the information it provides for future decisions. Solving these challenges will enable application of RL in domains such as personalised education, digital health, robotics, and the smart grid.

Carl Rasmussen SUPER_PER

Subjects by relevance
  1. Robots
  2. Decision making
  3. Machine learning
  4. Learning
  5. Automation
  6. Smart grids
  7. Robotics
  8. Algorithms
  9. Optimisation

Extracted key phrases
  1. Efficient Reinforcement Learning
  2. RL system
  3. RL method
  4. Data
  5. Traditional model
  6. True model
  7. Dynamical system
  8. Certain decision
  9. Future decision
  10. Reasoning technique similar
  11. Algorithm
  12. Term value
  13. Datum
  14. Optimal action
  15. Autonomous robotic

Related Pages

UKRI project entry

UK Project Locations