activity
20172022
most citedA Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms

122 citations · 436 across the 20 of their papers we have counts for

collaborators

28 papers

cs.LG20224 cited

Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning

Riashat Islam, Hongyu Zang, Anirudh Goyal +6

Goal-conditioned reinforcement learning (RL) is a promising direction for training agents that are capable of solving multiple tasks and reach a diverse set of objectives. How to \…

cs.AI2022

Coordinating Policies Among Multiple Agents via an Intelligent Communication Channel

Dianbo Liu, Vedant Shah, Oussama Boussif +6

In Multi-Agent Reinforcement Learning (MARL), specialized channels are often introduced that allow agents to communicate directly with one another. In this paper, we propose an alt…

cs.LG20226 cited

Retrieval-Augmented Reinforcement Learning

Anirudh Goyal, Abram L. Friesen, Andrea Banino +13

Most deep reinforcement learning (RL) algorithms distill experience into parametric behavior policies or value functions via gradient updates. While effective, this approach has se…

cs.LG20219 cited

Variational Causal Networks: Approximate Bayesian Inference over Causal Structures

Yashas Annadani, Jonas Rothfuss, Alexandre Lacoste +4

Learning the causal structure that underlies data is a crucial step towards robust real-world decision making. The majority of existing work in causal inference focuses on determin…

cs.LG20215 cited

Fast and Slow Learning of Recurrent Independent Mechanisms

Kanika Madan, Nan Rosemary Ke, Anirudh Goyal +2

Decomposing knowledge into interchangeable pieces promises a generalization advantage when there are changes in distribution. A learning agent interacting with its environment is l…

cs.LG20218 cited

Transformers with Competitive Ensembles of Independent Mechanisms

Alex Lamb, Di He, Anirudh Goyal +4

An important development in deep learning from the earliest MLPs has been a move towards architectures with structural inductive biases which enable the model to keep distinct sour…