Conferences, PrePrints and Journals:
- Vincent Francois-Lavet, Peter Henderson, Riashat Islam, Marc G. Bellemare, Joelle Pineau. “An Introduction to Deep Reinforcement Learning”. (Paper)
Journal : Foundations and Trends in Machine Learning, 2018 - Arash Tavakoli, Vitaly Levdik, Riashat Islam, Petar Kormushev. “Prioritizing Starting States for Reinforcement Learning”. (Paper) (Under Submission)
- Anirudh Goyal, Riashat Islam, DJ Strouse, Zafarali Ahmed, Hugo Larochelle, Matthew Botvinick, Sergey Levine, Yoshua Bengio. InfoBot: Transfer and Exploration via the Information Bottleneck (ICLR 2019)
- Philip Bachman, Riashat Islam, Alessandro Sordoni, Zafarali Ahmed.
“VFunc : A Deep Generative Model for Functions”. arxiv, 2018 (Paper) - Peter Henderson*, Riashat Islam*, Philip Bachman, Joelle Pineau, Doina Precup, David Meger. “Deep Reinforcement Learning that Matters”.
AAAI 2018 (Paper) (Science Magazine) (Blogpost) - David Krueger*, Chin-Wei Huang*, Riashat Islam, Ryan Turner, Aaron Courville. “Bayesian Hypernetworks”. Arxiv (Paper)
- Maziar Gomrokchi, Susan Amin, Riashat Islam, Doina Precup. “Persistence Length-Based Exploration in Deep Reinforcement Learning”. In Submission, 2017
- Yarin Gal, Riashat Islam, Zoubin Ghahramani. “Deep Bayesian Active Learning with Image Data”. ICML 2017 (Paper | Code | Poster | Slides)
- Bogdan Mazoure*, Riashat Islam*. “Alpha-Divergences in Variational Dropout” arxiv preprint, 2017 (Paper)
- H. M. Tarek Ullah, Zishan Ahmed Onik, Riashat Islam, Dip Nandi. “Alzheimer’s Disease And Dementia Detection From 3D Brain MRI Data Using Deep Convolutional Neural Networks.”. I2CT 2017
Workshops :
- Anirudh Goyal, Riashat Islam, Zafarali Ahmed, Doina Precup, Matthew Botvinick, Hugo Larochelle, Sergey Levine and Yoshua Bengio
“InfoBot: Structured Exploration in Reinforcement Learning Using Information Bottleneck”. Exploration in Reinforcement Learning workshop, ICML 2018 - Philip Bachman, Riashat Islam, Zafarali Ahmed, Alessandro Sordoni.
“VFunc : A Deep Generative Model for Functions”. Prediction and Generative Modelling in Reinforcement Learning workshop, ICML 2018 (Paper) (Oral) - Khimya Khetarpal, Zafarali Ahmed, Andre Cianflone, Riashat Islam, Joelle Pineau “Re-Evaluate : Reproducibility in Evaluating Reinforcement Learning Algorithms”. Reproducibility in Machine Learning Workshop, ICML 2018 (Paper)
- Amy Zhang, Josh Romoff, Riashat Islam. “An Analysis of Optimization for Deep Reinforcement Learning”. Modern Trends in Nonconvex Optimization for Machine Learning workshop, ICML 2018
- David Krueger*, Chin-Wei Huang*, Riashat Islam, Ryan Turner, Alexandre Lacoste and Aaron Courville. “Bayesian Hypernetworks”.
Bayesian Deep Learning workshop NIPS 2017 (Paper) - Peter Henderson*, Thang Doan*, Riashat Islam and David Meger.
“Bayesian Policy Gradients via Alpha-Divergence Dropout Inference”.
Bayesian Deep Learning workshop, NIPS 2017 (Paper) (Poster) - Riashat Islam*, Peter Henderson*, Maziar Gomrokchi, Doina Precup. “Reprodicibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control”. Reproducibility in Machine Learning workshop, ICML 2017 (Paper | Poster | Code)
- Riashat Islam*, Peter Henderson*, Doina Precup.
Contributed talk at Reinforcement Learning workshop, ICML 2017 (Slides) - Maziar Gomrokchi, Susan Amin, Riashat Islam, Harsh Satija, Doina Precup. “Using Locally Self-Avoiding Random Walks for Exploration in Reinforcement Learning”. RLDM 2017
- Yarin Gal, Riashat Islam, Zoubin Ghahramani. “Active Learning with Image Data”. Bayesian Deep Learning workshop, NIPS 2016 (Paper | Poster)
* Equal Contributions
Profile :
Paper Reviewing and Program Committee :
- NIPS 2018 Continual Learning workshop
- NIPS 2018 Bayesian Deep Learning workshop
- NIPS 2018 MainConference
- NIPS 2017 Bayesian Deep Learning workshop
Thesis :
- Riashat Islam, Yarin Gal, Zoubin Ghahramani. “Active Learning Image Data using Uncertainty in Deep Learning”. Masters Thesis, University of Cambridge, 2016 (Thesis | Poster | Code)
- Riashat Islam, Guy Lever, John Shawe-Taylor. “Improving Convergence of Deterministic Policy Gradient Methods in Reinforcement Learning”. Undergraduate Thesis, University College London, 2015 (Thesis | Code)
Others :
- Riashat Islam*, Peter Henderson*, Maziar Gomrokchi, Doina Precup. “Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control”, Montreal AI Symposium, 2017
Other Notes (Unpublished) :
- Deterministic Intra-Option Policy Gradient Theorem (Report)
- Option Critic in Reproducing Kernel Hilbert Space (Report)
Technical Reports/Projects :
- Riashat Islam. “Exploration in Continuous Control Reinforcement Learning” (Slides)
- Riashat Islam, Catherine McGhan, Richard Murray. “Improved State Estimation and Control for Resilient Spacecraft Executive”. SURF 2017, Caltech and NASA JPL (Report | Slides)
- Riashat Islam. “Large Vocabulary Speech Recognition” (Report)
- Riashat Islam. “Speech Recognition with GMM-HMMs” (Report)
- Riashat Islam, Jiameng Gao, Vera Johne. “Unifying Review of Variational Inference and Learning using Deep Directed Latent Variable Models” (Report | Poster)
- Riashat Islam. “Keyword Spotting” (Report)
- Riashat Islam. “Statistical Machine Translation” (Slides)
- Riashat Islam. “Reinforcement Learning for Spoken Dialogue Systems” (Report)
- Riashat Islam. “Basic Algorithms in Reinforcement Learning” (Report)
- Riashat Islam. “Playing Blackjack with Reinforcement Learning” (Report)
- Riashat Islam. “Cost-Sensitive Decision Tree Classifiers” (Report)
- Riashat Islam. “Gaussian Processes” (Report)
- Riashat Islam. “Weighted Automata using OpenFST” (Report)
- Riashat Islam. “Statistical Speech Synthesis” (Report)