ICLR

Learning to Ground Decentralized Multi-Agent Communication with Contrastive Learning

Yat Long Lo, Biswa Sengupta

Journal ref EmeCom at ICLR 2022

Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching

Pierre-Alexandre Kamienny, Jean Tarbouriech, Sylvain Lamprier, Alessandro Lazaric, Ludovic Denoyer

Comments ICLR 2022

Long-tailed Recognition by Routing Diverse Distribution-Aware Experts

Xudong Wang, Long Lian, Zhongqi Miao, Ziwei Liu, Stella X. Yu

Comments Accepted at ICLR 2021 (Spotlight); Add experiments on Swin Transformer

Oracle Guided Image Synthesis with Relative Queries

Alec Helbling, Christopher John Rozell, Matthew O'Shaughnessy, Kion Fallah

Comments Published at the International Conference on Learning Representations 2022, Workshop on Deep Generative Models for Highly Structured Data

Dynamic Noises of Multi-Agent Environments Can Improve Generalization: Agent-based Models meets Reinforcement Learning

Mohamed Akrout, Amal Feriani, Bob McLeod

Comments Accepted to the Gamification and Multiagent Solutions Workshop at ICLR 2022

Training Structured Neural Networks Through Manifold Identification and Variance Reduction

Zih-Syuan Huang, Ching-pei Lee

Journal ref The 10th International Conference on Learning Representations, 2022

The Geometry of Memoryless Stochastic Policy Optimization in Infinite-Horizon POMDPs

Johannes Müller, Guido Montúfar

Comments Camera ready version for ICLR 2022, 45 pages, 8 figures

Journal ref Proceedings of the 10th International Conference on Learning Representations (ICLR 2022)

Training Data Generating Networks: Shape Reconstruction via Bi-level Optimization

Biao Zhang, Peter Wonka

Comments Accepted to ICLR 2022

Watts: Infrastructure for Open-Ended Learning

Aaron Dharna, Charlie Summers, Rohin Dasari, Julian Togelius, Amy K. Hoover

Comments ICLR Workshop on Agent Learning in Open-Endedness (ALOE 2022)

Vitruvion: A Generative Model of Parametric CAD Sketches

Ari Seff, Wenda Zhou, Nick Richardson, Ryan P. Adams

Comments ICLR camera ready

Journal ref ICLR 2022

On Evaluation Metrics for Graph Generative Models

Rylee Thompson, Boris Knyazev, Elahe Ghalebi, Jungtaek Kim, Graham W. Taylor

Comments Published as a conference paper at ICLR 2022

Trivial or impossible -- dichotomous data difficulty masks model differences (on ImageNet and beyond)

Kristof Meding, Luca M. Schulze Buschoff, Robert Geirhos, Felix A. Wichmann

Comments Published as a conference paper at ICLR 2022

Binding Actions to Objects in World Models

Ondrej Biza, Robert Platt, Jan-Willem van de Meent, Lawson L. S. Wong, Thomas Kipf

Comments Published at the ICLR 2022 workshop on Objects, Structure and Causality

On the role of population heterogeneity in emergent communication

Mathieu Rita, Florian Strub, Jean-Bastien Grill, Olivier Pietquin, Emmanuel Dupoux

Comments International Conference on Learning Representations (ICLR) 2022

Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future

Harshavardhan Kamarthi, Alexander Rodríguez, B. Aditya Prakash

Comments 15 pages, 8 figures, To appear in ICLR 2022

Learning Value Functions from Undirected State-only Experience

Matthew Chang, Arjun Gupta, Saurabh Gupta

Comments ICLR 2022. Project website at https://matthewchang.github.io/latent_action_qlearning_site

Know Thy Student: Interactive Learning with Gaussian Processes

Rose E. Wang, Mike Wu, Noah Goodman

Comments ICLR 2022 From Cells to Societies: Collective Learning Across Scales Workshop

SIReN-VAE: Leveraging Flows and Amortized Inference for Bayesian Networks

Jacobie Mouton, Steve Kroon

Comments To appear in ICLR 2022 workshop Deep Generative Models for Highly Structured Data

Graphical Residual Flows

Jacobie Mouton, Steve Kroon

Comments To appear in ICLR 2022 workshop Deep Generative Models for Highly Structured Data

No One Representation to Rule Them All: Overlapping Features of Training Methods

Raphael Gontijo-Lopes, Yann Dauphin, Ekin D. Cubuk

Journal ref International Conference on Learning Representations (ICLR) 2022

Skill-based Meta-Reinforcement Learning

Taewook Nam, Shao-Hua Sun, Karl Pertsch, Sung Ju Hwang, Joseph J Lim

Comments ICLR 2022. Project page at https://namsan96.github.io/SiMPL

Task-Induced Representation Learning

Jun Yamada, Karl Pertsch, Anisha Gunjal, Joseph J. Lim

Comments International Conference on Learning Representations (ICLR), 2022

HyperNCA: Growing Developmental Networks with Neural Cellular Automata

Elias Najarro, Shyam Sudhakaran, Claire Glanois, Sebastian Risi

Comments Paper accepted as a conference paper at ICLR 'From Cells to Societies' workshop 2022

Do Users Benefit From Interpretable Vision? A User Study, Baseline, And Dataset

Leon Sixt, Martin Schuessler, Oana-Iuliana Popescu, Philipp Weiß, Tim Landgraf

Comments Published at ICLR 2022

Imitation Learning from Observations under Transition Model Disparity

Tanmay Gangwani, Yuan Zhou, Jian Peng

Comments ICLR 2022 camera-ready

Collaborative Auto-Curricula Multi-Agent Reinforcement Learning with Graph Neural Network Communication Layer for Open-ended Wildfire-Management Resource Distribution

Philipp Dominic Siedler

Comments Gamification and Multiagent Solutions Workshop at the 10th International Conference on Learning Representations (ICLR 2022)

$π$BO: Augmenting Acquisition Functions with User Beliefs for Bayesian Optimization

Carl Hvarfner, Danny Stoll, Artur Souza, Marius Lindauer, Frank Hutter, Luigi Nardi

Comments 9 pages, 4 figures, Accepted as poster for ICLR 2022

ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind

Yuanfei Wang, Fangwei Zhong, Jing Xu, Yizhou Wang

Comments ICLR 2022

Understanding Dimensional Collapse in Contrastive Self-supervised Learning

Li Jing, Pascal Vincent, Yann LeCun, Yuandong Tian

Comments In Proceedings of the 10th International Conference on Learning Representations (ICLR) 2022

Journal ref ICLR 2022

Network Augmentation for Tiny Deep Learning

Han Cai, Chuang Gan, Ji Lin, Song Han

Comments ICLR 2022