Related papers: BFTBrain: Adaptive BFT Consensus with Reinforcemen…

Several research projects have shown that Byzantine fault tolerance (BFT) is practical today in terms of performance. Deficiencies in other aspects might still be an obstacle to a more wide-spread deployment in real-world applications. One…

We present new protocols for Byzantine state machine replication and Byzantine agreement in the synchronous and authenticated setting. The celebrated PBFT state machine replication protocol tolerates $f$ Byzantine faults in an asynchronous…

Inherent client drifts caused by data heterogeneity, as well as vulnerability to Byzantine attacks within the system, hinder effective model training and convergence in federated learning (FL). This paper presents two new frameworks, named…

Vote-based blockchains construct a state machine replication (SMR) system among participating nodes, using Byzantine Fault Tolerance (BFT) consensus protocols to transition from one state to another. Currently, they rely on either…

Reinforcement learning (RL) has shown great effectiveness in quadrotor control, enabling specialized policies to develop even human-champion-level performance in single-task scenarios. However, these specialized policies often struggle with…

In this work, we investigate the synergy between supervised fine-tuning (SFT) and reinforcement learning (RL) in developing strong reasoning models. We begin by curating the SFT training data through two scaling strategies: increasing the…

Reinforcement learning (RL) based investment strategies have been widely adopted in portfolio management (PM) in recent years. Nevertheless, most RL-based approaches may often emphasize on pursuing returns while ignoring the risks of the…

Model-free or learning-based control, in particular, reinforcement learning (RL), is expected to be applied for complex robotic tasks. Traditional RL requires a policy to be optimized is state-dependent, that means, the policy is a kind of…

Blockchain technology has been proposed as a new infrastructure technology for a wide variety of novel applications. Blockchains provide an immutable record of transactions, making them useful when business actors do not trust each other.…

The concept of distributed consensus originated in the 1970s and gained widespread attention following Leslie Lamport's influential publication on the Byzantine Generals Problem in the 1980s. Over the past five decades, distributed…

This paper introduces a deep learning-based framework for resilient decision fusion in adversarial multi-sensor networks, providing a unified mathematical setup that encompasses diverse scenarios, including varying Byzantine node…

Federated learning is a newly emerging distributed learning framework that facilitates the collaborative training of a shared global model among distributed participants with their privacy preserved. However, federated learning systems are…

RL post-training for LLMs has been widely scaled to enhance reasoning and tool-using capabilities. However, RL post-training interleaves training and inference workloads, exposing the system to faults from both sides. Existing fault…

The safety-critical scenarios of artificial intelligence (AI), such as autonomous driving, Internet of Things, smart healthcare, etc., have raised critical requirements of trustworthy AI to guarantee the privacy and security with reliable…

In this paper, we investigate the challenging framework of Byzantine-robust training in distributed machine learning (ML) systems, focusing on enhancing both efficiency and practicality. As distributed ML systems become integral for complex…

The growing literature of Federated Learning (FL) has recently inspired Federated Reinforcement Learning (FRL) to encourage multiple agents to federatively build a better decision-making policy without sharing raw trajectories. Despite its…

The view synchronization problem lies at the heart of many Byzantine Fault Tolerant (BFT) State Machine Replication (SMR) protocols in the partial synchrony model, since these protocols are usually based on views. Liveness is guaranteed if…

Safe reinforcement learning (RL) is a standard paradigm for safety-critical decision making. However, real-world safety constraints can be complex, subjective, and even hard to explicitly specify. Existing works on constraint inference rely…

Existing Byzantine fault-tolerant (BFT) consensus protocols address only threshold failures, where the participating nodes fail independently of each other, each one fails equally likely, and the protocol's guarantees follow from a simple…

Sample efficiency has been a key issue in reinforcement learning (RL). An efficient agent must be able to leverage its prior experiences to quickly adapt to similar, but new tasks and situations. Meta-RL is one attempt at formalizing and…