6 citations · 25 across the 11 of their papers we have counts for
11 papers
Offline Multitask Representation Learning for Reinforcement Learning
Haque Ishfaq, Thanh Nguyen-Tang, Songtao Feng +4
We study offline multitask representation learning in reinforcement learning (RL), where a learner is provided with an offline dataset from different tasks that share a common repr…
Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games
Songtao Feng, Ming Yin, Yu-Xiang Wang +2
The problem of two-player zero-sum Markov games has recently attracted increasing interests in theoretical studies of multi-agent reinforcement learning (RL). In particular, for fi…
Non-stationary Reinforcement Learning under General Function Approximation
Songtao Feng, Ming Yin, Ruiquan Huang +3
General function approximation is a powerful tool to handle large state and action spaces in a broad range of reinforcement learning (RL) scenarios. However, theoretical understand…
Provable Benefit of Multitask Representation Learning in Reinforcement Learning
Yuan Cheng, Songtao Feng, Jing Yang +2
As representation learning becomes a powerful technique to reduce sample complexity in reinforcement learning (RL) in practice, theoretical understanding of its advantage is still…
Information Freshness for Timely Detection of Status Changes
Songtao Feng, Jing Yang
In this paper, we aim to establish the connection between Age of Information (AoI) in network theory, information uncertainty in information theory, and detection delay in time ser…
Adaptive Coding for Information Freshness in a Two-user Broadcast Erasure Channel
Songtao Feng, Jing Yang
In this paper, we investigate the impact of coding on the Age of Information (AoI) in a two-user broadcast symbol erasure channel with feedback. We assume each update consists of $…
Age-Optimal Transmission of Rateless Codes in an Erasure Channel
Songtao Feng, Jing Yang
In this paper, we examine a status updating system where updates generated by the source are sent to the monitor through an erasure channel. We assume each update consists of s…
When to Preempt? Age of Information Minimization under Link Capacity Constraint
Boyu Wang, Songtao Feng, Jing Yang
In this paper, we consider a scenario where a source continuously monitors an object and sends time-stamped status updates to a destination through a rate-limited link. We assume u…
Learning to Attend On Essential Terms: An Enhanced Retriever-Reader Model for Open-domain Question Answering
Jianmo Ni, Chenguang Zhu, Weizhu Chen +1
Open-domain question answering remains a challenging task as it requires models that are capable of understanding questions and answers, collecting useful information, and reasonin…
To Skip or to Switch? Minimizing Age of Information under Link Capacity Constraint
Boyu Wang, Songtao Feng, Jing Yang
Consider a scenario where a source continuously monitors an object and sends time-stamped status updates to a destination through a rate-limited link. In order to measure the "fres…
Optimal Status Updating for an Energy Harvesting Sensor with a Noisy Channel
Songtao Feng, Jing Yang
Consider an energy harvesting sensor continuously monitors a system and sends time-stamped status update to a destination. The destination keeps track of the system status through…