Explore the latest in Facebook Research through publications

All Publications

January 5, 2021 Nirbhay Modhe, Prithvijit Chattopadhyay, Mohit Sharma, Abhishek Das, Devi Parikh, Dhruv Batra, Ramakrishna Vedantam
Paper

IR-VIC: Unsupervised Discovery of Sub-goals for Transfer in RL

We propose a novel framework to identify subgoals useful for exploration in sequential decision making tasks under partial observability.
Paper
January 1, 2021 Mahmoud Assran, Michael Rabbat
Paper

Asynchronous Gradient-Push

We consider a multi-agent framework for distributed optimization where each agent has access to a local smooth strongly convex function, and the collective goal is to achieve consensus on the parameters that minimize the sum of the agents’ local functions. We propose an algorithm wherein each agent operates asynchronously and independently of the other agents.
Paper
August 17, 2020 Lei Xiao, Salah Nouri, Matt Chapman, Alexander Fix, Douglas Lanman, Anton Kaplanyan
Paper

Neural Supersampling for Real-time Rendering

Following the recent advances in image and video superresolution in computer vision, we propose a machine learning approach that is specifically tailored for high-quality upsampling of rendered content in real-time applications.
Paper
August 14, 2020 Mahmoud Assran, Michael Rabbat
Paper

On the Convergence of Nesterov’s Accelerated Gradient Method in Stochastic Settings

We study Nesterov’s accelerated gradient method with constant step-size and momentum parameters in the stochastic approximation setting (unbiased gradients with bounded variance) and the finite-sum setting (where randomness is due to sampling mini-batches). To build better insight into the behavior of Nesterov’s method in stochastic settings, we focus throughout on objectives that are smooth, strongly-convex, and twice continuously differentiable.
Paper
August 13, 2020 Tanmay Shankar, Abhinav Gupta
Paper

Learning Robot Skills with Temporal Variational Inference

In this paper, we address the discovery of robotic options from demonstrations in an unsupervised manner. Specifically, we present a framework to jointly learn low-level control policies and higher-level policies of how to use them from demonstrations of a robot performing various tasks.
Paper
July 25, 2020 Viet Ha-Thuc, Avishek Dutta, Ren Mao, Matthew Wood, Yunli Liu
Paper

A Counterfactual Framework for Seller-Side A/B Testing on Marketplaces

We propose a counterfactual framework for seller-side A/B testing. The key idea is that items in the treatment group are ranked the same regardless of experiment exposure rate.
Paper
July 19, 2020 Jungdam Won, Deepak Gopinath, Jessica Hodgins
Paper

A Scalable Approach to Control Diverse Behaviors for Physically Simulated Characters

Human characters with a broad range of natural looking and physically realistic behaviors will enable the construction of compelling interactive experiences. In this paper, we develop a technique for learning controllers for a large set of heterogeneous behaviors.
Paper
July 14, 2020 Amy Zhang, Clare Lyle, Shagun Sodhani, Angelos Filos, Marta Kwiatkowska, Joelle Pineau, Yarin Gal, Doina Precup
Paper

Invariant Causal Prediction for Block MDPs

Generalization across environments is critical for the successful application of reinforcement learning algorithms to real-world challenges. In this paper, we consider the problem of learning abstractions that generalize in block MDPs, families of environments with a shared latent state space, and dynamics structure over that latent space, but varying observations.
Paper
July 14, 2020 Gregory Farquhar, Laura Gustafson, Zeming Lin, Shimon Whiteson, Nicolas Usunier, Gabriel Synnaeve
Paper

Growing Action Spaces

In complex tasks, such as those with large combinatorial action spaces, random exploration may be too inefficient to achieve meaningful learning progress. In this work, we use a curriculum of progressively growing action spaces to accelerate learning.
Paper
July 13, 2020 Jungo Kasai, James Cross, Marjan Ghazvininejad, Jiatao Gu
Paper

Non-autoregressive Machine Translation with Disentangled Context Transformer

State-of-the-art neural machine translation models generate a translation from left to right and every step is conditioned on the previously generated tokens. The sequential nature of this generation process causes fundamental latency in inference since we cannot generate multiple tokens in each sentence in parallel. We propose an attention-masking based model, called Disentangled Context (DisCo) transformer, that simultaneously generates all tokens given different contexts.
Paper