Anirudh Goyal
Cited by
Cited by
An actor-critic algorithm for sequence prediction
D Bahdanau, P Brakel, K Xu, A Goyal, R Lowe, J Pineau, A Courville, ...
ICLR'17, 2016
Professor forcing: A new algorithm for training recurrent networks
A Goyal, A Lamb, Y Zhang, S Zhang, AC Courville, Y Bengio
Advances In Neural Information Processing Systems, 4601-4609, 2016
Zoneout: Regularizing rnns by randomly preserving hidden activations
D Krueger, T Maharaj, J Kramár, M Pezeshki, N Ballas, NR Ke, A Goyal, ...
ICLR'17, 2016
Z-forcing: Training stochastic recurrent networks
A Goyal, A Sordoni, MA Côté, NR Ke, Y Bengio
Advances in neural information processing systems, 6713-6723, 2017
A meta-transfer objective for learning to disentangle causal mechanisms
Y Bengio, T Deleu, N Rahaman, R Ke, S Lachapelle, O Bilaniuk, A Goyal, ...
ICLR'20, 2019
InfoBot: Transfer and Exploration via the Information Bottleneck
A Goyal, R Islam, D Strouse, Z Ahmed, M Botvinick, H Larochelle, ...
ICLR'19, 2019
Sparse Attentive Backtracking: Temporal credit assignment through reminding
NR Ke, A Goyal, O Bilaniuk, J Binas, MC Mozer, C Pal, Y Bengio
Advances in Neural Information Processing Systems, 7651-7662, 2018
Recall traces: Backtracking models for efficient reinforcement learning
A Goyal, P Brakel, W Fedus, T Lillicrap, S Levine, H Larochelle, Y Bengio
ICLR'19, 2018
State-reification networks: Improving generalization by modeling the distribution of hidden representations
A Lamb, J Binas, A Goyal, S Subramanian, I Mitliagkas, D Kazakov, ...
ICML'19, arXiv preprint arXiv:1804.02485, 2019
Recurrent independent mechanisms
A Goyal, A Lamb, J Hoffmann, S Sodhani, S Levine, Y Bengio, ...
arXiv preprint arXiv:1909.10893, 2019
Maximum Entropy Generators for Energy-Based Models
R Kumar, A Goyal, A Courville, Y Bengio
arXiv preprint arXiv:1901.08508, 2019
Learning dynamics model in reinforcement learning by incorporating the long term future
NR Ke, A Singh, A Touati, A Goyal, Y Bengio, D Parikh, D Batra
ICLR'19, 2019
Variational walkback: Learning a transition operator as a stochastic recurrent net
A Goyal, NR Ke, S Ganguli, Y Bengio
Advances in Neural Information Processing Systems, 4392-4402, 2017
Extending the framework of equilibrium propagation to general dynamics
B Scellier, A Goyal, J Binas, T Mesnard, Y Bengio
Learning neural causal models from unknown interventions
NR Ke, O Bilaniuk, A Goyal, S Bauer, H Larochelle, B Schölkopf, ...
arXiv preprint arXiv:1910.01075, 2019
Actual: Actor-critic under adversarial learning
A Goyal, NR Ke, A Lamb, RD Hjelm, C Pal, J Pineau, Y Bengio
arXiv preprint arXiv:1711.04755, 2017
Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives
A Goyal, S Sodhani, J Binas, XB Peng, S Levine, Y Bengio
ICLR'20, arXiv preprint arXiv:1906.10667, 2019
Small-gan: Speeding up gan training using core-sets
S Sinha, H Zhang, A Goyal, Y Bengio, H Larochelle, A Odena
arXiv preprint arXiv:1910.13540, 2019
Learning powerful policies by using consistent dynamics model
S Sodhani, A Goyal, T Deleu, Y Bengio, S Levine, J Tang
arXiv preprint arXiv:1906.04355, 2019
Learning to combine top-down and bottom-up signals in recurrent neural networks with attention over modules
S Mittal, A Lamb, A Goyal, V Voleti, M Shanahan, G Lajoie, M Mozer, ...
arXiv preprint arXiv:2006.16981, 2020
The system can't perform the operation now. Try again later.
Articles 1–20