Reinforcement learning (RL) is a powerful tool for solving complex
decis...
Offline reinforcement learning aims to utilize datasets of previously
ga...
Communication is crucial for solving cooperative Multi-Agent Reinforceme...
Covering skill (a.k.a., option) discovery has been developed to improve ...
The dominant text generation models compose the output by sequentially
s...
Whether or not stocks are predictable has been a topic of concern for
de...
This paper proposes to learn Multi-task, Multi-modal Direct Acyclic Grap...
Multi-Agent Experience Replay (MER) is a key component of off-policy
rei...
Robust network design, which aims to guarantee network availability unde...
Imperfect Information Games (IIGs) offer robust models for scenarios whe...
We present PandaGPT, an approach to emPower large lANguage moDels with v...
Multi-Agent Reinforcement Learning (MARL) is an increasingly important
r...
Multi-task Imitation Learning (MIL) aims to train a policy capable of
pe...
Experience replay is crucial for off-policy reinforcement learning (RL)
...
Value function factorization methods have become a dominant approach for...
Multi-Agent Reinforcement Learning (MARL) is a promising area of researc...
Learning with multiple modalities is crucial for automated brain tumor
s...
To solve the problems of reduced accuracy and prolonging convergence tim...
Open-ended text generation with autoregressive language models (LMs) is ...
Learning rich skills through temporal abstractions without supervision o...
Bayesian optimization (BO) is a popular global optimization scheme for
s...
The use of options can greatly accelerate exploration in reinforcement
l...
Hierarchical Imitation Learning (HIL) has been proposed to recover
highl...
Multi-agent reinforcement learning (MARL) has witnessed significant prog...
Video Instance Segmentation (VIS) aims to simultaneously classify, segme...
Text generation is of great importance to many natural language processi...
In today's world, computer networks have become vulnerable to numerous
a...
One of the biggest challenges in Federated Learning (FL) is that client
...
Covering option discovery has been developed to improve the exploration ...
Value function factorization via centralized training and decentralized
...
The virtual try-on system has gained great attention due to its potentia...
Recent research on dialogue response selection has been mainly focused o...
Recent single-channel speech enhancement methods usually convert wavefor...
Communication protocol security is among the most significant challenges...
We introduce Merlion, an open-source machine learning library for time
s...
Gradient-based training in federated learning is known to be vulnerable ...
Deep reinforcement learning (RL) is a powerful framework to train
decisi...
Gradient quantization is an emerging technique in reducing communication...
With the freight delivery demands and shipping costs increasing rapidly,...
Since the pre-trained language models are widely used, retrieval-based
o...
We study the coarse-grained selection module in retrieval-based chatbot....
In order to improve the accuracy and resolution for transmit beamspace
m...
Predicting the future behavior of moving agents is essential for real wo...
Currently, open-domain generative dialog systems have attracted consider...
As consumers are increasingly engaged in social networking and E-commerc...
Open-domain generative dialogue systems have attracted considerable atte...
Voice traffic prediction is significant for network deployment optimizat...
Prior work in multi-task learning has mainly focused on predictions on a...
Despite the multi-turn open-domain dialogue systems have attracted more ...
Detecting code clones is crucial in various software engineering tasks. ...