Publications

Conferences, PrePrints and Journals:

  1. Riashat Islam, Jayakumar Subramanian, Raihan Seraj, Pierre-Luc Bacon, Doina Precup. “Entropy Regularization with Discounted Future State Distributions in Policy Gradient” (under submission)
  2. Riashat Islam, Raihan Seraj, Samin Yeasar Arnob, Doina Precup. “Doubly Robust Off-Policy Actor-Critic Algorithms for Reinforcement Learning” (under submission)
  3. Riashat Islam, Deepak Sharma, Komal Teru, Doina Precup. “Off-Policy Policy Gradient Algorithms by Minimizing the State Distribution Shift” (under submission)
  4. Riashat Islam, Zafarali Ahmed, Doina Precup. “Marginalized State Distribution Entropy Regularization in Policy Optimization” (under submission)
  5. Martin Klissarov*, Riashat Islam*, Khimya Khetarpal, Doina Precup. “Variational State Encoding as Intrinsic Motivation in Reinforcement Learning” (under submission)
  6. 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
  7. Arash Tavakoli, Vitaly Levdik, Riashat Islam, Petar Kormushev. “Prioritizing Starting States for Reinforcement Learning”. (Paper) (Under Submission)
  8. 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) (Poster)
  9. Philip Bachman, Riashat Islam, Alessandro Sordoni, Zafarali Ahmed.
    “VFunc : A Deep Generative Model for Functions”. arxiv, 2018 (Paper)
  10. Peter Henderson*, Riashat Islam*, Philip Bachman, Joelle Pineau, Doina Precup, David Meger. “Deep Reinforcement Learning that Matters”.
    AAAI 2018 (Paper) (Science Magazine) (Blogpost)
  11. David Krueger*, Chin-Wei Huang*, Riashat Islam, Ryan Turner, Aaron Courville. “Bayesian Hypernetworks”. Arxiv (Paper)
  12. Maziar Gomrokchi, Susan Amin, Riashat Islam, Doina Precup. “Persistence Length-Based Exploration in Deep Reinforcement Learning”. In Submission, 2017 
  13. Yarin Gal, Riashat Islam, Zoubin Ghahramani. “Deep Bayesian Active Learning with Image Data”. ICML 2017 (Paper | Code | Poster | Slides) 
  14. Bogdan Mazoure*, Riashat Islam*. “Alpha-Divergences in Variational Dropout” arxiv preprint, 2017 (Paper)
  15. 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 :

  1. Riashat Islam, Jayakumar Subramanian, Raihan Seraj, Pierre-Luc Bacon, Doina Precup. “Entropy Regularization with Discounted Future State Distributions in Policy Gradient”. The Optimization Foundations for Reinforcement Learning workshop, NeurIPS 2019
  2. Riashat Islam, Deepak Sharma, Komal Teru, Doina Precup. “Off-Policy Policy Gradient Algorithms by Minimizing the State Distribution Shift”. Deep Reinforcement Learning workshop, NeurIPS 2019
  3. Riashat Islam, Zafarali Ahmed, Doina Precup. “Marginalized State Distribution Entropy Regularization in Policy Optimization”. Deep Reinforcement Learning workshop, NeurIPS 2019
  4. Riashat Islam, Raihan Seraj, Samin Yeasar Arnob, Doina Precup. “Doubly Robust Off-Policy Actor-Critic Algorithms for Reinforcement Learning”. Safety and Robustness in Decision Making workshop, NeurIPS 2019
  5. Disha Shrivastava, Eeshan Gunesh Dhekane, Riashat Islam. “Transfer Learning by Modelling Distribution over Policies”. Multi-Task and Lifelong Reinforcement Learning, ICML 2019
  6. Riashat Islam*, Martin Klissarov*, Khimya Khetarpal, Doina Precup. “Variational State Encoding as Intrinsic Motivation in Reinforcement Learning”. Task Agnostic Reinforcement Learning workshop, ICLR 2019 (Paper)
  7. Srinivas Venkattaramanujam, Riashat Islam, Doina Precup. “Automatic Curriculum Generation Via Task Perturbations For Reinforcement Learning”, Task Agnositc Reinforcement Learning workshop, ICLR 2019
  8. Riashat Islam, Zafarali Ahmed, Pierre-Luc Bacon, Doina Precup
    “Off-Policy Policy Gradient Theorem with Logarithmic Mappings”, RLDM 2019
  9. Riashat Islam*, Samin Yeasar Arnob*, Doina Precup
    “Doubly Robust Estimators in Off-Policy Actor-Critic Algorithms”, (Spotlight), RLDM 2019
  10. Martin Klissarov*, Riashat Islam*, Khimya Khetarpal, Doina Precup.
    “Variational State Encoding as Intrinsic Motivation in Reinforcement Learning”, RLDM 2019
  11. Arash Tavakoli*, Vitaly Levdik*, Riashat Islam, Peter Kormushev.
    “Prioritizing Starting States for Reinforcement Learning”, RLDM 2019
  12. Andre Cianflone, Zafarali Ahmed, Riashat Islam, Avishek Joey Bose, William L. Hamilton. “Discrete off-policy policy gradient using continuous relaxations”, RLDM 2019
  13. 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
  14. 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)
  15. 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)
  16. 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
  17. David Krueger*, Chin-Wei Huang*, Riashat Islam, Ryan Turner, Alexandre Lacoste and Aaron Courville. “Bayesian Hypernetworks”.
    Bayesian Deep Learning workshop NIPS 2017 (Paper)
  18. 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)
  19. 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)
  20. Riashat Islam*, Peter Henderson*, Doina Precup.
    Contributed talk at Reinforcement Learning workshop, ICML 2017 (Slides)
  21. Maziar Gomrokchi, Susan Amin, Riashat Islam, Harsh Satija, Doina Precup. “Using Locally Self-Avoiding Random Walks for Exploration in Reinforcement Learning”. RLDM 2017
  22. Yarin Gal, Riashat Islam, Zoubin Ghahramani. “Active Learning with Image Data”. Bayesian Deep Learning workshop, NIPS 2016 (Paper | Poster)

* Equal Contributions

Profile :


Google Scholar Profile

DBLP Profile

Arxiv

 

Paper Reviewing and Program Committee :

  1. AAAI 2020 Main Conference
  2. NeurIPS 2019 Deep Reinforcement Learning workshop
  3. NeurIPS 2019 Bayesian Deep Learning workshop 
  4. ICLR 2020 Main Conference
  5. NeurIPS 2019 Main Conference
  6. ICML 2019 : Multi-Task and Lifelong Reinforcement Learning workshop
  7. UAI 2019 Main Conference
  8. ICML 2019 Main Conference
  9. NeurIPS 2018 Continual Learning workshop
  10. NeurIPS 2018 Bayesian Deep Learning workshop
  11. NeurIPS 2018 MainConference
  12. NeurIPS 2017 Bayesian Deep Learning workshop

 

Thesis :

  1. Riashat Islam, Yarin Gal, Zoubin Ghahramani. “Active Learning Image Data using Uncertainty in Deep Learning”. Masters Thesis, University of Cambridge, 2016 (Thesis | Poster | Code)
  2. 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 :

  1. 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) :

  1. Deterministic Intra-Option Policy Gradient Theorem (Report)
  2. Option Critic in Reproducing Kernel Hilbert Space (Report)

 

Technical Reports/Projects :

  1. Riashat Islam. “Exploration in Continuous Control Reinforcement Learning” (Slides)
  2. Riashat Islam, Catherine McGhan, Richard Murray. “Improved State Estimation and Control for Resilient Spacecraft Executive”.  SURF 2017, Caltech and NASA JPL (Report | Slides)
  3. Riashat Islam. “Large Vocabulary Speech Recognition” (Report)
  4. Riashat Islam. “Speech Recognition with GMM-HMMs” (Report)
  5. Riashat Islam, Jiameng Gao, Vera Johne. “Unifying Review of Variational Inference and Learning using Deep Directed Latent Variable Models” (Report | Poster)
  6. Riashat Islam. “Keyword Spotting” (Report)
  7. Riashat Islam. “Statistical Machine Translation” (Slides)
  8. Riashat Islam. “Reinforcement Learning for Spoken Dialogue Systems” (Report)
  9. Riashat Islam. “Basic Algorithms in Reinforcement Learning” (Report)
  10. Riashat Islam. “Playing Blackjack with Reinforcement Learning” (Report)
  11. Riashat Islam. “Cost-Sensitive Decision Tree Classifiers” (Report)
  12. Riashat Islam. “Gaussian Processes” (Report)
  13. Riashat Islam. “Weighted Automata using OpenFST” (Report)
  14. Riashat Islam. “Statistical Speech Synthesis” (Report)