some of my recent projects and news.



J. Chakravorty, P.N. Ward, J. Roy, M. Chevalier-Boisvert, S. Basu, A. Lupu, D. Precup (2020) “Option-Critic in cooperative multi-agent systems” Extnded Abstract at the International Conference on Autonomous Agents and Mutli-Agent Systems (AAMAS) 2020.

P.N. Ward*, A. Smofsky*, A. J. Bose (2019) “Improving Exploration in Soft-Actor-Critic with Normalizing Flows Policies” Invertible Neural Networks and Normalizing Flows Workshop at the International Conference on Machine Learning (ICML) 2019. (code)


Several lectures and tutorials given while helping teach an intro to Reinforcement Learning course at McGill for the Master of Managemement in Analytics program.

Intro to Python for Machine Learning tutorial given at McGill

Other Projects

Reimplementing simple policy gradient methods like REINFORCE and one-step Actor-Critic on OpenAI gym environments

Created a flexible GridWorld environment in python to run tabular Reinforcement Learning algorithms such as Dynamic programming, Tabular Temporal Differencing (TD) and Monte Carlo methods.

In class Kaggle competition to classify the largest digit within an image with multiple digits. This work was done with Daoud Piracha.