Articles


KL Divergence Regularization for RL

Intro Regularization is a very common practice in machine learning. In supervized learning it is used to reduce model complexity. It also helps prevent the model from over fitting the test data. In RL because of the availablility of limitless data regularization does not need to be used to reduce …


Interfacing with Simulators for RL

Intro These days many people want to use one of many new libraries written in python to train deep learning models. In general Python has many powerful and easy to use libraries for performing machine learning. However, many appications that generate data that we want to learn are written in …

Towards Computer Assisted Crowd Aware Architectural Design

With this work we build upon prevous work in crowd optimization. Leveraging optimization methods previously used to assist users in architectural design tasks. Abstract We present a preliminary exploration of an architectural optimization process towards a computational tool for designing environments (e.g., building floor plans). Using dynamic crowd simulators …

Using synthetic crowds to inform building pillar placements

Abstract We present a preliminary exploration of synthetic crowds towards computational tools for informing the design of environments (e.g., building floor plans). Feedback and automatic design processes are developed from exploring crowd behaviours and metrics derived from simulations of environments in density stressed scenarios, such as evacuations. Computational approaches …