Anirudh Goyal

发表

InfoBot: Transfer and Exploration via the Information Bottleneck pdf

Sergey Levine, Yoshua Bengio, Hugo Larochelle, 2019, ICLR.

Recall Traces: Backtracking Models for Efficient Reinforcement Learning pdf

Sergey Levine, Yoshua Bengio, Hugo Larochelle, 2018, ICLR.

Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations pdf

Yoshua Bengio, Hugo Larochelle, Tegan Maharaj, 2016, ICLR.

Sparse Attentive Backtracking: Temporal CreditAssignment Through Reminding

Christopher Joseph Pal, Yoshua Bengio, Jonathan Binas, 2018, NeurIPS.

A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms pdf

Christopher Joseph Pal, Yoshua Bengio, Tristan Deleu, 2019, ICLR.

Learning Neural Causal Models from Unknown Interventions pdf

Yoshua Bengio, Hugo Larochelle, Anirudh Goyal, 2019, ArXiv.

State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations pdf

Ioannis Mitliagkas, Sandeep Subramanian, Yoshua Bengio, 2019, ICML.

Variational Walkback: Learning a Transition Operator as a Stochastic Recurrent Net

Surya Ganguli, Yoshua Bengio, Anirudh Goyal, 2017, NIPS.

The Variational Walkback Algorithm

Nan Rosemary Ke, Yoshua Bengio, Anirudh Goyal, 2016 .

Professor Forcing: A New Algorithm for Training Recurrent Networks

Yoshua Bengio, Aaron C. Courville, Ying Zhang, 2016, NIPS.

O ct 2 01 9 S MALL-GAN : S PEEDING UP GAN T RAINING USING C ORES ETS

Yoshua Bengio, H. Larochelle, Anirudh Goyal, 2019 .

L EARNING THE A RROW OF T IME FOR P ROBLEMS IN R EINFORCEMENT L EARNING

Yoshua Bengio, Anirudh Goyal, Nasim Rahaman, 2020 .

Sparse Attentive Backtracking : Towards Efficient Credit Assignment In Recurrent Networks

Nan Rosemary Ke, Yoshua Bengio, Anirudh Goyal, 2017 .

Learning Neural Causal Models from Unknown Interventions

Nan Rosemary Ke, Yoshua Bengio, H. Larochelle, 2019, ArXiv.

Inductive Biases for Deep Learning of Higher-Level Cognition

Yoshua Bengio, Anirudh Goyal, 2020, ArXiv.

Learning Powerful Policies by Using Consistent Dynamics Model pdf

Sergey Levine, Yoshua Bengio, Tristan Deleu, 2019, ArXiv.

Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives pdf

Sergey Levine, Yoshua Bengio, Jonathan Binas, 2019, ICLR.

Extending the Framework of Equilibrium Propagation to General Dynamics

Yoshua Bengio, Jonathan Binas, Anirudh Goyal, 2018, ICLR.

Towards Jumpy Planning

Aaron C. Courville, Anirudh Goyal, Alexander Neitz, 2019 .

InfoBot: Structured Exploration in ReinforcementLearning Using Information Bottleneck

Sergey Levine, Yoshua Bengio, Hugo Larochelle, 2019 .

Modeling the Long Term Future in Model-Based Reinforcement Learning

Yoshua Bengio, Amanpreet Singh, Anirudh Goyal, 2018, ICLR.

Untangling tradeoffs between recurrence and self-attention in artificial neural networks

Yoshua Bengio, Anirudh Goyal, Giancarlo Kerg, 2020, NeurIPS.

An Actor-Critic Algorithm for Structured Prediction

Joelle Pineau, Yoshua Bengio, Anirudh Goyal, 2016 .

Learning powerful policies and better dynamics models by encouraging consistency

Yoshua Bengio, Tristan Deleu, Anirudh Goyal, 2018 .

Retrieval-Augmented Reinforcement Learning

Nan Rosemary Ke, Adrià Puigdomènech Badia, T. Lillicrap, 2022, ICML.

Coordinating Policies Among Multiple Agents via an Intelligent Communication Channel

N. Heess, Anirudh Goyal, Y. Bengio, 2022, ArXiv.

Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning

Nan Rosemary Ke, Anirudh Goyal, Alex Lamb, 2022, NeurIPS.

On the Generalization and Adaption Performance of Causal Models

Nan Rosemary Ke, Anirudh Goyal, Y. Bengio, 2022, ArXiv.

Transformers with Competitive Ensembles of Independent Mechanisms

Yoshua Bengio, Anirudh Goyal, Alex Lamb, 2021, ArXiv.

Factorizing Declarative and Procedural Knowledge in Structured, Dynamical Environments

Sergey Levine, Alex Lamb, Anirudh Goyal, 2021, ICLR.

L EARNING BY D IRECTIONAL G RADIENT D ESCENT

Ivo Danihelka, Matteo Hessel, Anirudh Goyal, 2022 .

Inductive biases for deep learning of higher-level cognition

Yoshua Bengio, Anirudh Goyal, 2020, Proceedings of the Royal Society A.

Discrete Key-Value Bottleneck

Anirudh Goyal, B. Scholkopf, Y. Bengio, 2022, ArXiv.

Learning to Induce Causal Structure

Danilo Jimenez Rezende, Nan Rosemary Ke, Jane X. Wang, 2022, ICLR.

Stateful active facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning

N. Heess, Anirudh Goyal, Y. Bengio, 2022, ArXiv.

Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning

Anirudh Goyal, Riashat Islam, Alex Lamb, 2022, ArXiv.

Leveraging the Third Dimension in Contrastive Learning

Sumukh K Aithal, Anirudh Goyal, Alex Lamb, 2023, ArXiv.

On Disentangled Representations Learned from Correlated Data

Francesco Locatello, Anirudh Goyal, Bernhard Scholkopf, 2020, International Conference on Machine Learning.

GFlowOut: Dropout with Generative Flow Networks

Bonaventure F. P. Dossou, Chris C. Emezue, Anirudh Goyal, 2022, International Conference on Machine Learning.

Learning by Directional Gradient Descent

Ivo Danihelka, Matteo Hessel, H. V. Hasselt, 2022, ICLR.

Recurrent Independent Mechanisms pdf

Sergey Levine, Bernhard Schölkopf, Yoshua Bengio, 2019, ICLR.

Episodes Meta Sequence S 2 Fast Update Slow Update Fast Update Slow Update

Rosemary Nan Ke, B. Schölkopf, Anirudh Goyal, 2021 .

Towards Causal Representation Learning

Yoshua Bengio, Francesco Locatello, Anirudh Goyal, 2021, ArXiv.

On Disentangled Representations Learned from Correlated Data

B. Schölkopf, Anirudh Goyal, Francesco Locatello, 2020, ICML.

Z-Forcing: Training Stochastic Recurrent Networks

Yoshua Bengio, Anirudh Goyal, Marc-Alexandre Côté, 2017, NIPS.

Learning Neural Causal Models with Active Interventions

Nan Rosemary Ke, B. Schölkopf, Anirudh Goyal, 2021, ArXiv.

Discrete Key-Value Bottleneck

Anirudh Goyal, B. Scholkopf, Y. Bengio, 2022, ArXiv.

An Actor-Critic Algorithm for Sequence Prediction pdf

Joelle Pineau, Yoshua Bengio, Aaron C. Courville, 2016, ICLR.

Maximum Entropy Generators for Energy-Based Models pdf

Yoshua Bengio, Aaron C. Courville, Anirudh Goyal, 2019, ArXiv.

Top-K Training of GANs: Improving Generators by Making Critics Less Critical pdf

Colin Raffel, Anirudh Goyal, Augustus Odena, 2020, ArXiv.

Small-GAN: Speeding Up GAN Training Using Core-sets pdf

Yoshua Bengio, Hugo Larochelle, Han Zhang, 2019, ICML.

Fortified Networks: Improving the Robustness of Deep Networks by Modeling the Manifold of Hidden Representations pdf

Ioannis Mitliagkas, Sandeep Subramanian, Yoshua Bengio, 2018, ArXiv.

Fast and Slow Learning of Recurrent Independent Mechanisms pdf

Anirudh Goyal, Kanika Madan, Yoshua Bengio, 2021, ICLR.

The Variational Bandwidth Bottleneck: Stochastic Evaluation on an Information Budget pdf

Yoshua Bengio, Sergey Levine, Anirudh Goyal, 2020, ICLR.

DIBS: Diversity inducing Information Bottleneck in Model Ensembles pdf

Hugo Larochelle, Anirudh Goyal, Animesh Garg, 2020, AAAI.

Spotlight Attention: Robust Object-Centric Learning With a Spatial Locality Prior

Anirudh Goyal, Y. Bengio, M. Mozer, 2023, ArXiv.

Learning the Arrow of Time for Problems in Reinforcement Learning

Yoshua Bengio, Anirudh Goyal, Steffen Wolf, 2020, ICLR.

Learning the Arrow of Time pdf

Yoshua Bengio, Anirudh Goyal, Steffen Wolf, 2019, ArXiv.

Cycle Consistency Driven Object Discovery

Anirudh Goyal, Y. Bengio, Aniket Didolkar, 2023, ArXiv.

Neural Production Systems

Nan Rosemary Ke, N. Heess, C. Blundell, 2021, NeurIPS.

Variational Causal Networks: Approximate Bayesian Inference over Causal Structures pdf

Alexandre Lacoste, Anirudh Goyal, Stefan Bauer, 2021, ArXiv.

GFlowOut: Dropout with Generative Flow Networks

Bonaventure F. P. Dossou, Chris C. Emezue, Anirudh Goyal, 2022, ICML.

Discrete Key-Value Bottleneck

B. Schölkopf, Anirudh Goyal, Y. Bengio, 2022, ICML.

Generalization of Equilibrium Propagation to Vector Field Dynamics pdf

Yoshua Bengio, Jonathan Binas, Anirudh Goyal, 2018, ArXiv.

S TATEFUL ACTIVE FACILITATOR : C OORDINATION AND E NVIRONMENTAL H ETEROGENEITY IN C OOPERATIVE M ULTI -A GENT R EINFORCEMENT L EARNING

N. Heess, Anirudh Goyal, Y. Bengio, 2022 .

Professor Forcing: A New Algorithm for Training Recurrent Networks

Aaron C. Courville, Yoshua Bengio, Anirudh Goyal, 2016, NIPS.

Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future pdf

Yoshua Bengio, Amanpreet Singh, Anirudh Goyal, 2019, ArXiv.

ACtuAL: Actor-Critic Under Adversarial Learning pdf

Joelle Pineau, Christopher Joseph Pal, Yoshua Bengio, 2017, ArXiv.

TC-VAE: Uncovering Out-of-Distribution Data Generative Factors

Anirudh Goyal, Cristian Meo, J. Dauwels, 2023, ArXiv.

Spatially Structured Recurrent Modules

Bernhard Schölkopf, Anirudh Goyal, Muhammad Waleed Gondal, 2021, ICLR.

A Theory for Emergence of Complex Skills in Language Models

Sanjeev Arora, Anirudh Goyal, 2023, ArXiv.

DiscoGen: Learning to Discover Gene Regulatory Networks

Danilo Jimenez Rezende, Nan Rosemary Ke, Jane X. Wang, 2023, bioRxiv.

Toward Causal Representation Learning

Nan Rosemary Ke, Anirudh Goyal, Nal Kalchbrenner, 2021, Proceedings of the IEEE.

Communication Topologies Between Learning Agents in Deep Reinforcement Learning pdf

Alex Pentland, Abhimanyu Dubey, Anirudh Goyal, 2019, ArXiv.

A Theory for Emergence of Complex Skills in Language Models

Sanjeev Arora, Anirudh Goyal, 2023, ArXiv.

Gemini: A Family of Highly Capable Multimodal Models

Tara N. Sainath, Dalia El Badawy, Reinald Kim Amplayo, 2023, ArXiv.

Sparse Attentive Backtracking: Long-Range Credit Assignment in Recurrent Networks pdf

Christopher Joseph Pal, Yoshua Bengio, Jonathan Binas, 2017, ArXiv.

Skill-Mix: a Flexible and Expandable Family of Evaluations for AI models

Anirudh Goyal, Jonah Brown-Cohen, Arushi Gupta, 2023, ArXiv.

Gemini: A Family of Highly Capable Multimodal Models

Tara N. Sainath, Dalia El Badawy, Reinald Kim Amplayo, 2023, ArXiv.

Stateful active facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning

N. Heess, Anirudh Goyal, Y. Bengio, 2022, ICLR.

Zero-Shot Object-Centric Representation Learning

G. Martius, Anirudh Goyal, Y. Bengio, 2024, 2408.09162.