A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
[SensorFetch code] [code]
The project aims to predict five kinds of emotions of pedestrains from sensory data of cellphones. The following procedures were performed: I developed an Android Mobile App SensorFetch to record sensory data; A total of 30 pedestrians were recruited to walk with cellphones in hand under induced emotions; I regressed sensory data onto emotion labels that pedestrians reported. The results demonstrated a weak correlation and required further measures to accurately capture pedestrian emotionals.
Page not found. Your pixels are in another canvas.
This is a page not in th emain menu
Junning Huang*, Sirui Xie*, Jiankai Xun, Qiurui Ma, Chunxiao Liu, Bolei Zhou,
The Conference on Robot Learning (CoRL), 2020
[paper] [project page] [code]
we propose a hybrid framework to learn neural decisions in the classical modular pipeline through end-to-end imitation learning. This hybrid framework can preserve the merits of the classical pipeline such as the strict enforcement of physical and logical constraints while learning complex driving decisions from data.
Yongzhao Wang*, Qiurui Ma*, Michael Wellman,
In Empirical Game Theoretic Analysis (EGTA), game models are iteratively extended to include the Nash Equilibrium of the underlying true games. The Strategy Exploration process dictates which new strategies to add to the game models next based on current available information. We investigate the methodological considerations in evaluating different strategy exploration processes in EGTA and highlight a consistency criteria that past literatures violate.
In this project, we apply double q-learning for long and short trading on twenty years of oil derivatives. My work envolved first scraped 20 years of oil derivative data from Bloomberg and Yahoo Finance; then implemented a support-resistance line visualization tool to better analyze and feature engineer; finally implemented a double dqn module to long or short the derivative, with its performance beating the benchmark buy-and-hold strategy
Qiurui Ma*, Sirui Xie*,
[Contact me for detailed design and implementation for IP reasons]
In this study, we bring uncertainty estimation to model based RL for autonomous driving. The model is parenthesized by a bayesian neural network to approximate PILCO and dropouts are used to estimate the uncertainty. We further train a multilayer perceptron as a controller, whose gradient could flow through the model network. We demonstrate that our model could output uncertainty towards its projections, and could navigate safely in complex environments.
Qiurui Ma*, Duo Zhang*, Brandon Jew, Sriram Sankararaman,
[code] [poster] [presentation] [report on data simulation]
In this study, we deconvolute builk-level gene expressions into cell-type-specific gene expressions with cell-type weights using bayesian models, circumventing the centrifusion that traditional methods require to acqure cell-type specific gene expressions. We then associate specific gene expressions with phenotypes on UKBiobank blood tissue data.