Spremljaj
Riashat Islam
Riashat Islam
Research Scientist
Preverjeni e-poštni naslov na mail.mcgill.ca - Domača stran
Naslov
Navedeno
Navedeno
Leto
Deep reinforcement learning that matters
P Henderson*, R Islam*, P Bachman, J Pineau, D Precup, D Meger
Proceedings of 32nd AAAI Conference on Artificial Intelligence (AAAI-18), 2017
24502017
Deep Bayesian Active Learning with Image Data
Y Gal, R Islam, Z Ghahramani
Proceedings of the 34th International Conference on Machine Learning (ICML-17), 2017
19542017
An introduction to deep reinforcement learning
V François-Lavet, P Henderson, R Islam, MG Bellemare, J Pineau
Foundations and Trends® in Machine Learning 11 (3-4), 219-354, 2018
18252018
Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control
R Islam, P Henderson, M Gomrokchi, D Precup
Reproducibility in Machine Learning Workshop, ICML 2017, 2017
3282017
Bayesian Hypernetworks
D Krueger, CW Huang, R Islam, R Turner, A Lacoste, A Courville
arXiv preprint arXiv:1710.04759, 2017
1782017
InfoBot : Transfer and Exploration via the Information Bottleneck
A Goyal, R Islam, DJ Strouse, Z Ahmed, H Larochelle, M Botvinick, ...
International Conference on Learning Representations (ICLR) 2019, 2018
1692018
Guaranteed discovery of controllable latent states with multi-step inverse models
A Lamb, R Islam, Y Efroni, A Didolkar, D Misra, D Foster, L Molu, R Chari, ...
arXiv preprint arXiv:2207.08229, 2022
232022
Re-evaluate: Reproducibility in evaluating reinforcement learning algorithms
K Khetarpal, Z Ahmed, A Cianflone, R Islam, J Pineau
222018
Bayesian Policy Gradients via Alpha Divergence Dropout Inference
P Henderson, T Doan, R Islam, D Meger
Bayesian Deep Learning Workshop, NIPS 2017, 2017
182017
Marginalized state distribution entropy regularization in policy optimization
R Islam, Z Ahmed, D Precup
arXiv preprint arXiv:1912.05128, 2019
162019
Agent-controller representations: Principled offline rl with rich exogenous information
R Islam, M Tomar, A Lamb, Y Efroni, H Zang, A Didolkar, D Misra, X Li, ...
ICML 2023; arXiv:2211.00164, 2023
142023
Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning
R Islam, H Zang, A Goyal, A Lamb, K Kawaguchi, X Li, R Laroche, ...
NeurIPS 2022, 2022
142022
Active Learning for High Dimensional Inputs using Bayesian Convolutional Neural Networks
R Islam, Y Gal, Z Ghahramani
University of Cambridge, Masters Thesis, 2016
142016
Exploring restart distributions
A Tavakoli, V Levdik, R Islam, CM Smith, P Kormushev
arXiv preprint arXiv:1811.11298, 2018
122018
Guaranteed discovery of control-endogenous latent states with multi-step inverse models
A Lamb, R Islam, Y Efroni, A Didolkar, D Misra, D Foster, L Molu, R Chari, ...
arXiv preprint arXiv:2207.08229, 2022
112022
Variational state encoding as intrinsic motivation in reinforcement learning
M Klissarov, R Islam, K Khetarpal, D Precup
Task-Agnostic Reinforcement Learning Workshop at Proceedings of the …, 2019
112019
Behavior prior representation learning for offline reinforcement learning
H Zang, X Li, J Yu, C Liu, R Islam, RTD Combes, R Laroche
arXiv preprint arXiv:2211.00863, 2022
92022
Off-Policy Policy Gradient Algorithms by Constraining the State Distribution Shift
R Islam, KK Teru, D Sharma, J Pineau
https://arxiv.org/abs/1911.06970, 2019
92019
Entropy regularization with discounted future state distribution in policy gradient methods
R Islam, R Seraj, PL Bacon, D Precup
arXiv preprint arXiv:1912.05104, 2019
82019
VFunc: a Deep Generative Model for Functions
P Bachman, R Islam, A Sordoni, Z Ahmed
Prediction and Generative Modeling in Reinforcement Learning workshop, ICML 2018, 2018
82018
Sistem trenutno ne more izvesti postopka. Poskusite znova pozneje.
Članki 1–20