Related papers: SquirRL: Automating Attack Analysis on Blockchain …

Large language model-based agents make mistakes, yet critique can often guide the same model toward correct behavior. However, when critique is removed, the model may fail again on the same query, indicating that it has not internalized the…

Many researchers have proposed replacing the aggregation server in federated learning with a blockchain system to improve privacy, robustness, and scalability. In this approach, clients would upload their updated models to the blockchain…

An emerging blockchain protocol design pattern leverages the asymmetry between the computational effort in performing versus verifying tasks. For example, cryptographic validity proofs (e.g., SNARKS) require the prover to expend significant…

Preference-based reinforcement learning (PbRL) provides a natural way to align RL agents' behavior with human desired outcomes, but is often restrained by costly human feedback. To improve feedback efficiency, most existing PbRL methods…

We consider deep deterministic policy gradient (DDPG) in the context of reinforcement learning with sparse rewards. To enhance exploration, we introduce a search procedure, \emph{${\epsilon}{t}$-greedy}, which generates exploratory options…

This paper introduces a comprehensive framework designed to analyze and secure decision-support systems trained with Deep Reinforcement Learning (DRL), prior to deployment, by providing insights into learned behavior patterns and…

Safe reinforcement learning (RL) trains a policy to maximize the task reward while satisfying safety constraints. While prior works focus on the performance optimality, we find that the optimal solutions of many safe RL problems are not…

Reinforcement Learning (RL) with rubric-based rewards has recently shown remarkable progress in enhancing general reasoning capabilities of Large Language Models (LLMs), yet still suffers from ineffective exploration confined to curent…

Deep reinforcement learning (DRL) has achieved significant breakthroughs in various tasks. However, most DRL algorithms suffer a problem of generalizing the learned policy which makes the learning performance largely affected even by minor…

GHOST, like the longest-chain protocol, is a chain selection protocol and its capability in resisting selfish mining attack has been validated in imperfect blockchains of Bitcoin and its variants (Bitcoin-like). This paper explores an…

Robust Reinforcement Learning (RL) focuses on improving performances under model errors or adversarial attacks, which facilitates the real-life deployment of RL agents. Robust Adversarial Reinforcement Learning (RARL) is one of the most…

This work proposes a novel proof-of-work blockchain incentive scheme such that, barring exogenous motivations, following the protocol is guaranteed to be the optimal strategy for miners. Our blockchain takes the form of a directed acyclic…

We examine global non-asymptotic convergence properties of policy gradient methods for multi-agent reinforcement learning (RL) problems in Markov potential games (MPG). To learn a Nash equilibrium of an MPG in which the size of state space…

This paper establishes a new and comprehensive theoretical analysis for the application of reinforcement learning (RL) in high-frequency market making. We bridge the modern RL theory and the continuous-time statistical models in…

Resource allocation plays a critical role in minimizing cycle time and improving the efficiency of business processes. Recently, Deep Reinforcement Learning (DRL) has emerged as a powerful technique to optimize resource allocation policies…

This paper introduces two metrics (cycle-based and memory-based metrics), grounded on a dynamical game-theoretic solution concept called sink equilibrium, for the evaluation, ranking, and computation of policies in multi-agent learning. We…

Different types of malicious activities have been flagged in multiple permissionless blockchains such as bitcoin, Ethereum etc. While some malicious activities exploit vulnerabilities in the infrastructure of the blockchain, some target its…

Motivated by governance models adopted in blockchain applications, we study the problem of selecting appropriate system updates in a decentralised way. Contrary to most existing voting approaches, we use the input of a set of motivated…

Increasing traffic demands, higher levels of automation, and communication enhancements provide novel design opportunities for future air traffic controllers (ATCs). This article presents a novel deep reinforcement learning (DRL) controller…

Recent works have demonstrated the vulnerability of Deep Reinforcement Learning (DRL) algorithms against training-time, backdoor poisoning attacks. The objectives of these attacks are twofold: induce pre-determined, adversarial behavior in…