Graph Neural Network (GNN)-based models have become the mainstream appro...
Evolutionary reinforcement learning (ERL) algorithms recently raise atte...
This paper studies a new problem, active learning with partial labels
(A...
Previous question-answer pair generation methods aimed to produce fluent...
In recent years, data-driven reinforcement learning (RL), also known as
...
Recommender systems now consume large-scale data and play a significant ...
Trajectory prediction has been a crucial task in building a reliable
aut...
Outlier exposure (OE) is powerful in out-of-distribution (OOD) detection...
Attaining the equilibrium state of a catalyst-adsorbate system is key to...
Knowing the learning dynamics of policy is significant to unveiling the
...
Contrastive learning has emerged as a premier method for learning
repres...
We proposed a new technique to accelerate sampling methods for solving
d...
Designing better deep networks and better reinforcement learning (RL)
al...
The mobile communication enabled by cellular networks is the one of the ...
In reinforcement learning applications like robotics, agents usually nee...
The latent world model provides a promising way to learn policies in a
c...
High-quality traffic flow generation is the core module in building
simu...
Deep Reinforcement Learning (Deep RL) and Evolutionary Algorithm (EA) ar...
Centralized Training with Decentralized Execution (CTDE) has been a very...
Adapting to the changes in transition dynamics is essential in robotic
a...
Unsupervised reinforcement learning (URL) poses a promising paradigm to ...
Lying on the heart of intelligent decision-making systems, how policy is...
Deriving a good variable selection strategy in branch-and-bound is essen...
To better exploit search logs and model users' behavior patterns, numero...
We investigate model-free multi-agent reinforcement learning (MARL) in
e...
In recent years, interest has arisen in using machine learning to improv...
Deep Reinforcement Learning (DRL) has been a promising solution to many
...
Precise congestion prediction from a placement solution plays a crucial ...
Learning to collaborate is critical in Multi-Agent Reinforcement Learnin...
Multi-agent reinforcement learning is difficult to be applied in practic...
Recent progress in state-only imitation learning extends the scope of
ap...
In cooperative multi-agent systems, agents jointly take actions and rece...
Model-based reinforcement learning methods achieve significant sample
ef...
We propose learning via retracing, a novel self-supervised approach for
...
Value estimation is one key problem in Reinforcement Learning. Albeit ma...
The MineRL competition is designed for the development of reinforcement
...
Exploration methods based on pseudo-count of transitions or curiosity of...
The backpropagation networks are notably susceptible to catastrophic
for...
Circuit routing has been a historically challenging problem in designing...
Deep Reinforcement Learning (DRL) and Deep Multi-agent Reinforcement Lea...
Discrete-continuous hybrid action space is a natural setting in many
pra...
Domain generalization aims to learn knowledge invariant across different...
Extending transfer learning to cooperative multi-agent reinforcement lea...
Cutting plane methods play a significant role in modern solvers for tack...
It is a long-standing question to discover causal relations among a set ...
One principled approach for provably efficient exploration is incorporat...
Modern information retrieval systems, including web search, ads placemen...
Recent progress in deep reinforcement learning (DRL) can be largely
attr...
Constructing agents with planning capabilities has long been one of the ...
Communicating with each other in a distributed manner and behaving as a ...