7 papers
ProDVI: Programmatic Dynamics Priors for Value Network Initialization
Xinwei Liu, Junyuan Liang, Jianting Zhang +1
Deep Reinforcement Learning (RL) is notoriously sample inefficient. One contributing factor is that RL agents are typically initialized from scratch, forcing them to acquire task-r…
Observation-Grounded Self-Predictive Reinforcement Learning for Visual Continuous Control
Xinwei Liu, Junyuan Liang, Jianting Zhang +1
Sample-efficient policy learning from pixels is a long-standing challenge in reinforcement learning (RL). Recent dynamics-based representation learning methods have significantly i…
NASDAQ: Normalized Observation Space Dynamics-Augmented Q-Learning
Xinwei Liu, Junyuan Liang, Zicong Hong +2
Augmenting model-free reinforcement learning (RL) with representations learned through observation dynamics prediction (observation-predictive RL) can improve sample efficiency and…
Lifefin: Escaping Mempool Explosions in DAG-based BFT
Jianting Zhang, Sen Yang, Alberto Sonnino +2
Directed Acyclic Graph (DAG)-based Byzantine Fault-Tolerant (BFT) protocols have emerged as promising solutions for high-throughput blockchains. By decoupling data dissemination fr…
Beluga: Block Synchronization for BFT Consensus Protocols
Tasos Kichidis, Lefteris Kokoris-Kogias, Arun Koshy +4
Modern high-throughput BFT consensus protocols use streamlined push-pull mechanisms to disseminate blocks and keep happy-path performance optimal. Yet state-of-the-art designs lack…
Five Minutes of DDoS Brings down Tor: DDoS Attacks on the Tor Directory Protocol and Mitigations
Zhongtang Luo, Jianting Zhang, Akshat Neerati +1
The Tor network offers network anonymity to its users by routing their traffic through a sequence of relays. A group of nine directory authorities maintains information about all a…