UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning
Comments Published at ICML 2021
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning
Comments Published at the International Conference on Machine Learning (ICML) 2021
Improving Generalization in Meta-learning via Task Augmentation
Comments Accepted by ICML 2021
TempoRL: Learning When to Act
Comments Accepted at ICML'21
Bayesian Attention Belief Networks
Comments ICML 2021
Local Algorithms for Finding Densely Connected Clusters
Comments This work is accepted at ICML'21 for a long presentation
Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation
Comments ICML 2021 (Oral), Code at ICML21_OAXE" target="_blank" rel="noopener">https://github.com/tencent-ailab/ICML21_OAXE
PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training
Comments ICML 2021. First two authors contributed equally. Website: https://sites.google.com/view/icml21pebble Code: https://github.com/pokaxpoka/B_Pref
Which transformer architecture fits my data? A vocabulary bottleneck in self-attention
Comments ICML 2021
Implicit Regularization in Tensor Factorization
Comments Accepted to ICML 2021
Is Space-Time Attention All You Need for Video Understanding?
Comments Accepted to ICML 2021
Massively Parallel and Asynchronous Tsetlin Machine Architecture Supporting Almost Constant-Time Scaling
Comments Accepted to ICML 2021
Towards Open Ad Hoc Teamwork Using Graph-based Policy Learning
Comments Published in the 38th International Conference on Machine Learning (ICML 2021)
Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approach
Comments 28 pages. Accepted at ICML 2021
Self-Improved Retrosynthetic Planning
Comments Accepted to ICML 2021
Recovering AES Keys with a Deep Cold Boot Attack
Comments Accepted to ICML 2021
Learning to Price Against a Moving Target
Comments ICML 2021
WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points
Comments Published at ICML 2021
SMG: A Shuffling Gradient-Based Method with Momentum
Comments The 38th International Conference on Machine Learning (ICML 2021)
Black-box density function estimation using recursive partitioning
Comments International Conference on Machine Learning (ICML) 2021
Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration
Comments Accepted to Proceedings of the 38th International Conference on Machine Learning
Enhancing Robustness of Neural Networks through Fourier Stabilization
Comments Full version of an ICML 2021 paper
Private Counting from Anonymous Messages: Near-Optimal Accuracy with Vanishing Communication Overhead
Comments Originally appeared in ICML'20. This version contains a correction of calculation errors in Theorem 13 of the ICML'20 version
Self-supervised Graph-level Representation Learning with Local and Global Structure
Comments Accepted as Short Talk at International Conference on Machine Learning (ICML), 2021
Self-supervised and Supervised Joint Training for Resource-rich Machine Translation
Comments Accepted by ICML 2021
Principal Bit Analysis: Autoencoding with Schur-Concave Loss
Comments ICML 2021
Debiasing a First-order Heuristic for Approximate Bi-level Optimization
Comments Proceedings of the 38th International Conference on Machine Learning, PMLR 139, 2021. arXiv admin note: text overlap with arXiv:2006.03631
Learning Gradient Fields for Molecular Conformation Generation
Comments ICML 2021, Long talk
Directional Bias Amplification
Comments ICML 2021
Online Limited Memory Neural-Linear Bandits with Likelihood Matching
Comments ICML 2021. arXiv admin note: text overlap with arXiv:1901.08612
