HOME /

Talks

 

Here is a list of talks that I have given online (these are recorded): 

1) Multi Type Mean Field Reinforcement Learning - A.I. Socratic Circles (AISC), Toronto  (along with Matthew E. Taylor)

2) Multi Type Mean Field Reinforcement Learning - AAMAS 2020 

3) Partially Observable Mean Field Reinforcement Learning - AAMAS 2021

4) Recent Advances in Mean-Field RL methods - University of Alberta - Alberta Machine Intelligence Institute (Amii) AI seminar - (Introduction by Matthew E. Taylor)

5) Decentralized Mean Field Games - AAAI 2022 (Preliminary version. Full conference version can be found here). 

6) Decentralized Mean Field Games - University of Alberta - Alberta Machine Intelligence Institute (Amii) AI seminar - (Introduction by Matthew E. Taylor)

 

Here is a list of talks online by co-authors on joint research works (these are recorded): 

1) Extending Mean Field Reinforcement Learning to Partially Observable Environments, Agents of Multiple Types and Decentralized Learning: Machine Learning and Mean Field Games Seminar. - Talk by Pascal Poupart. 

2) The Effect of Q-function Reuse on the Total Regret of Tabular, Model-Free, Reinforcement Learning: Adaptive and Learning Agents (ALA) workshop at AAMAS 2021. - Talk by Volodymr Tkachuk. 

 

Here is a list of talks I have given at various points of time during my Masters and PhD: 

1) Deep Reinforcement Learning of Abstract Reasoning From Demonstrations - University of Waterloo 

2) Multi-Type Mean Field Reinforcement Learning - Conference of "Reinforcement Learning and Decision Making (RLDM)" - MCGill University, Montreal, Canada

3) Learning Multi-Agent Communication with Reinforcement Learning -  Conference of "Reinforcement Learning and Decision Making (RLDM)" - MCGill University, Montreal, Canada

4) Algorithmic Analysis and Improvements in Multi-Agent Reinforcement Learning for Partially Observable Setting - University of Waterloo (AI seminar) 

5) Wild Fire Response Using Game Theory and Reinforcement Learning - University of Waterloo 

6) Reinforcement Learning in SSP and Autonomous Driving domains - Borealis AI Toronto 

7) Reinforcement Learning for Determining Spread Dynamics of Spatially Spreading Processes with Emphasis on Forest Fires - MASc Seminar - University of Waterloo (MASc Seminar) 

8) Learning Forest Wildfire Dynamics from Satellite Images Using Reinforcement Learning - Conference of "Reinforcement Learning and Decision Making (RLDM)"  - University of Michgan, Ann Arbor, MI, USA