Reinforcement Learning

Good News in the UWECEML Lab

May 15, 2019

As spring continues to tease us with cold and rain we all could use some good news to cheer us up, well it seems we've been storing it up recently, there are several exciting achievements to highlight:

Read more about Good News in the UWECEML Lab
Bhalla, S., Subramanian, S.G. & Crowley, M., 2019. Training Cooperative Agents for Multi-Agent Reinforcement Learning. In Proc. of the 18th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2019). Montreal, Canada.
Deep Learning and back-propagation has been successfully used to perform centralized training with communication protocols among multiple agents in a cooperative environment. In this paper we present techniques for centralized training of Multi-Agent (Deep) Reinforcement Learning (MARL) using the model-free Deep Q-Network as the baseline model and message sharing between agents. We present a novel, scalable, centralized MARL training technique, which separates the message learning module from the policy module. The separation of these modules helps in faster convergence in complex domains like autonomous driving simulators. A second contribution uses the centrally trained model to bootstrap training of distributed, independent, cooperative agent policies for execution and thus addresses the challenges of noise and communication bottlenecks in real-time communication channels. This paper theoretically and empirically compares our centralized training algorithms to current research in the field of MARL. We also present and release a new OpenAI-Gym environment which can be used for multi-agent research as it simulates multiple autonomous cars driving cooperatively on a highway.
Fighting Fire with AI: Using Artificial Intelligence to Improve Modelling and Decision Making in Wildfire Management, at Banff International Research Station, Banff, Alberta, Canada, Friday, November 17, 2017:
I was invited to speak at this week-long workshop at the fabulous BIRS facility in Banff Alberta. The workshop was entitled "Forest and Wildland Fire Management: a Risk Management Perspective" which brought together a wide range of experts and stakeholders from across Canada as well as some researchers from around the world to discuss the latest research on Forest Fire Management. It was an incredibly productive week that built many new connections. Read more about Fighting Fire with AI: Using Artificial Intelligence to Improve Modelling and Decision Making in Wildfire Management
Using Deep Learning and Reinforcement Learning to Tame Spatially Spreading Processes, at University of Waterloo, Wednesday, October 25, 2017

This was an invited talk for the Waterloo Institute for Complexity and Innovation (WICI) seminar series. The talk was recorded and can be watched from WICI's website here.

Abstract:

Recent advances in Artificial Intelligence and Machine Learning (AI/ML) allow us to learn predictive models and control policies for larger, more complex systems than ever before. However, some important real world domains such as...

Read more about Using Deep Learning and Reinforcement Learning to Tame Spatially Spreading Processes
BIRC Workshop On Deep Learning In Medicine, at University Hospital, London, Ontario, Canada, Monday, August 28, 2017:

This all-day workshop brough together researchers, students and medical professionals from medical imaging, image processing and machine learning to discuss what the new class of machine learning algorithms known collectively as Deep Learning are, how they are and could be used for medicine and what the impacts for medicine as a whole are of this technology. The workshop was hosted by the Biomedical Imaging Research Centre (BIRC) at the University of Western Ontario. I gave an introductory...

Read more about BIRC Workshop On Deep Learning In Medicine