77 citations · 133 across the 21 of their papers we have counts for
13 papers · 1 filter
Enhancing PPO with Trajectory-Aware Hybrid Policies
Qisai Liu, Zhanhong Jiang, Hsin-Jung Yang +3
Proximal policy optimization (PPO) is one of the most popular state-of-the-art on-policy algorithms that has become a standard baseline in modern reinforcement learning with applic…
Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning
Prajwal Koirala, Zhanhong Jiang, Soumik Sarkar +1
In safe offline reinforcement learning (RL), the objective is to develop a policy that maximizes cumulative rewards while strictly adhering to safety constraints, utilizing only of…
DIMAT: Decentralized Iterative Merging-And-Training for Deep Learning Models
Nastaran Saadati, Minh Pham, Nasla Saleem +5
Recent advances in decentralized deep learning algorithms have demonstrated cutting-edge performance on various tasks with large pre-trained models. However, a pivotal prerequisite…
Neural PDE Solvers for Irregular Domains
Biswajit Khara, Ethan Herron, Zhanhong Jiang +8
Neural network-based approaches for solving partial differential equations (PDEs) have recently received special attention. However, the large majority of neural PDE solvers only a…
Distributed Online Non-convex Optimization with Composite Regret
Zhanhong Jiang, Aditya Balu, Xian Yeow Lee +3
Regret has been widely adopted as the metric of choice for evaluating the performance of online optimization algorithms for distributed, multi-agent systems. However, data/model va…
Asynchronous Training Schemes in Distributed Learning with Time Delay
Haoxiang Wang, Zhanhong Jiang, Chao Liu +3
In the context of distributed deep learning, the issue of stale weights or gradients could result in poor algorithmic performance. This issue is usually tackled by delay tolerant a…
MDPGT: Momentum-based Decentralized Policy Gradient Tracking
Zhanhong Jiang, Xian Yeow Lee, Sin Yong Tan +5
We propose a novel policy gradient method for multi-agent reinforcement learning, which leverages two different variance-reduction techniques and does not require large batches ove…
Cross-Gradient Aggregation for Decentralized Learning from Non-IID data
Yasaman Esfandiari, Sin Yong Tan, Zhanhong Jiang +4
Decentralized learning enables a group of collaborative agents to learn models using a distributed dataset without the need for a central parameter server. Recently, decentralized…
Decentralized Deep Learning using Momentum-Accelerated Consensus
Aditya Balu, Zhanhong Jiang, Sin Yong Tan +3
We consider the problem of decentralized deep learning where multiple agents collaborate to learn from a distributed dataset. While there exist several decentralized deep learning…
Spatiotemporal Attention for Multivariate Time Series Prediction and Interpretation
Tryambak Gangopadhyay, Sin Yong Tan, Zhanhong Jiang +2
Multivariate time series modeling and prediction problems are abundant in many machine learning application domains. Accurate interpretation of such prediction outcomes from a mach…
On Higher-order Moments in Adam
Zhanhong Jiang, Aditya Balu, Sin Yong Tan +3
In this paper, we investigate the popular deep learning optimization routine, Adam, from the perspective of statistical moments. While Adam is an adaptive lower-order moment based…
Online Robust Policy Learning in the Presence of Unknown Adversaries
Aaron J. Havens, Zhanhong Jiang, Soumik Sarkar
The growing prospect of deep reinforcement learning (DRL) being used in cyber-physical systems has raised concerns around safety and robustness of autonomous agents. Recent work on…
An unsupervised spatiotemporal graphical modeling approach to anomaly detection in distributed CPS
Chao Liu, Sambuddha Ghosal, Zhanhong Jiang +1
Modern distributed cyber-physical systems (CPSs) encounter a large variety of physical faults and cyber anomalies and in many cases, they are vulnerable to catastrophic fault propa…