相关论文: SquirRL: Automating Attack Analysis on Blockchain …

Multi-agent Inverse Reinforcement Learning (MAIRL) aims to recover agent reward functions from expert demonstrations. We characterize the feasible reward set in Markov games, identifying all reward functions that rationalize a given…

Aligning generative diffusion models with human preferences via reinforcement learning (RL) is critical yet challenging. Most existing algorithms are often vulnerable to reward hacking, such as quality degradation, over-stylization, or…

Smart contract-enabled blockchains allow building decentralized applications in which mutually-distrusted parties can work together. Recently, oracle services emerged to provide these applications with real-world data feeds. Unfortunately,…

Safe reinforcement learning (Safe RL) aims to ensure policy performance while satisfying safety constraints. However, most existing Safe RL methods assume benign environments, making them vulnerable to adversarial perturbations commonly…

This paper studies a fundamental problem regarding the security of blockchain on how the existence of multiple misbehaving pools influences the profitability of selfish mining. Each selfish miner maintains a private chain and makes it…

Leveraging the model's internal information as the self-reward signal in Reinforcement Learning (RL) has received extensive attention due to its label-free nature. While prior works have made significant progress in applying the Test-Time…

Reward-free exploration is a reinforcement learning setting studied by Jin et al. (2020), who address it by running several algorithms with regret guarantees in parallel. In our work, we instead give a more natural adaptive approach for…

Multi-agent policy-gradient methods have been shown to converge locally near stable Nash equilibria. Local convergence, however, does not determine which equilibrium is reached. We study this question through basin-entry probability with…

As AI systems grow more capable and autonomous, ensuring their safety and reliability requires not only model-level alignment but also strategic oversight of the humans and institutions involved in their development and deployment. Existing…

Reinforcement learning (RL) theory has largely focused on proving minimax sample complexity bounds. These require strategic exploration algorithms that use relatively limited function classes for representing the policy or value function.…

Inverse reinforcement learning (IRL) and dynamic discrete choice (DDC) models explain sequential decision-making by recovering reward functions that rationalize observed behavior. Flexible IRL methods typically rely on machine learning but…

Intrusion detection systems (IDS) generate a large number of false alerts which makes it difficult to inspect true positives. Hence, alert prioritization plays a crucial role in deciding which alerts to investigate from an enormous number…

Recent advances in automated essay scoring (AES) have shifted towards evaluating multiple traits to provide enriched feedback. Like typical AES systems, multi-trait AES employs the quadratic weighted kappa (QWK) to measure agreement with…

We introduce and study reward sharing schemes (RSS) that promote the fair formation of {\em stake pools}\ in collaborative projects that involve a large number of stakeholders such as the maintenance of a proof-of-stake (PoS) blockchain.…

With the rising emergence of decentralized and opportunistic approaches to machine learning, end devices are increasingly tasked with training deep learning models on-devices using crowd-sourced data that they collect themselves. These…

Bargaining games, where agents attempt to agree on how to split utility, are an important class of games used to study economic behavior, which motivates a study of online learning algorithms in these games. In this work, we tackle when…

In this work, we take a first step toward elucidating the mechanisms behind emergent exploration in unsupervised reinforcement learning. We study Single-Goal Contrastive Reinforcement Learning (SGCRL), a self-supervised algorithm capable of…

Smart contracts, the stateful programs running on blockchains, often rely on reports. Publishers are paid to publish these reports on the blockchain. Designing protocols that incentivize timely reporting is the prevalent reporting problem.…

Exploration is a fundamental aspect of reinforcement learning (RL), and its effectiveness is a deciding factor in the performance of RL algorithms, especially when facing sparse extrinsic rewards. Recent studies have shown the effectiveness…

As the second largest cryptocurrency by market capitalization and today's biggest decentralized platform that runs smart contracts, Ethereum has received much attention from both industry and academia. Nevertheless, there exist very few…