English
Related papers

Related papers: Reward Hacking as Equilibrium under Finite Evaluat…

200 papers

Language models are capable of iteratively improving their outputs based on natural language feedback, thus enabling in-context optimization of user preference. In place of human users, a second language model can be used as an evaluator,…

Computation and Language · Computer Science 2024-07-08 Jane Pan , He He , Samuel R. Bowman , Shi Feng

Existing benchmarks for AI reasoning provide limited insight into how closely these capabilities resemble human reasoning in naturalistic contexts. We present an adaptation of the Watson & Holmes detective tabletop game as a new benchmark…

Artificial Intelligence · Computer Science 2026-02-24 Thatchawin Leelawat , Lewis D Griffin

Reinforcement learning is commonly concerned with problems of maximizing accumulated rewards in Markov decision processes. Oftentimes, a certain goal state or a subset of the state space attain maximal reward. In such a case, the…

Artificial Intelligence · Computer Science 2024-08-23 Pavel Osinenko , Grigory Yaremenko , Georgiy Malaniya , Anton Bolychev , Alexander Gepperth

We study risk-sensitive multi-agent reinforcement learning under general-sum Markov games, where agents optimize the entropic risk measure of rewards with possibly diverse risk preferences. We show that using the regret naively adapted from…

Machine Learning · Computer Science 2024-05-07 Yingjie Fei , Ruitu Xu

This position paper argues that agentic AI systems should be designed and evaluated as \emph{marginal token allocation economies} rather than as text generators priced by the unit. We follow a single request -- a developer asking a coding…

Artificial Intelligence · Computer Science 2026-05-05 Siqi Zhu

Quantum error correction code discovery has relied on algebraic constructions with predetermined structure or computational search lacking mechanistic interpretability. We introduce a game-theoretic framework recasting code optimization as…

Quantum Physics · Physics 2026-05-28 Rubén Darío Guerrero

We present an alternative methodology for the analysis of algorithms, based on the concept of expected discounted reward. This methodology naturally handles algorithms that do not always terminate, so it can (theoretically) be used with…

Artificial Intelligence · Computer Science 2017-08-08 Andrew MacFie

We introduce a new model of stochastic bandits with adversarial corruptions which aims to capture settings where most of the input follows a stochastic pattern but some fraction of it can be adversarially changed to trick the algorithm,…

Machine Learning · Computer Science 2018-03-28 Thodoris Lykouris , Vahab Mirrokni , Renato Paes Leme

Existing accountability frameworks for AI systems, legal, ethical, and regulatory, rest on a shared assumption: for any consequential outcome, at least one identifiable person had enough involvement and foresight to bear meaningful…

Artificial Intelligence · Computer Science 2026-04-10 Haileleol Tibebu

Reinforcement learning (RL) has become a standard approach for post-training large language models and, more recently, for improving image generation models, which uses reward functions to enhance generation quality and human preference…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Yunqi Hong , Kuei-Chun Kao , Hengguang Zhou , Cho-Jui Hsieh

Artificial Intelligence (AI) systems are increasingly placed in positions where their decisions have real consequences, e.g., moderating online spaces, conducting research, and advising on policy. Ensuring they operate in a safe and…

Artificial Intelligence · Computer Science 2025-05-09 Joel Z. Leibo , Alexander Sasha Vezhnevets , William A. Cunningham , Sébastien Krier , Manfred Diaz , Simon Osindero

In many reinforcement learning (RL) applications, augmenting the task rewards with heuristic rewards that encode human priors about how a task should be solved is crucial for achieving desirable performance. However, because such heuristics…

Machine Learning · Computer Science 2025-07-09 Chi-Chang Lee , Zhang-Wei Hong , Pulkit Agrawal

Reward models are key in reinforcement learning from human feedback (RLHF) systems, aligning the model behavior with human preferences. Particularly in the math domain, there have been plenty of studies using reward models to align policies…

Machine Learning · Computer Science 2024-10-03 Sunghwan Kim , Dongjin Kang , Taeyoon Kwon , Hyungjoo Chae , Jungsoo Won , Dongha Lee , Jinyoung Yeo

Motivated by applications such as online labor markets we consider a variant of the stochastic multi-armed bandit problem where we have a collection of arms representing strategic agents with different performance characteristics. The…

Computer Science and Game Theory · Computer Science 2025-03-11 Seyed A. Esmaeili , Suho Shin , Aleksandrs Slivkins

We introduce DREAM, a deep reinforcement learning algorithm that finds optimal strategies in imperfect-information games with multiple agents. Formally, DREAM converges to a Nash Equilibrium in two-player zero-sum games and to an…

Machine Learning · Computer Science 2020-12-01 Eric Steinberger , Adam Lerer , Noam Brown

The growing prevalence of artificial intelligence (AI) in various applications underscores the need for agents that can successfully navigate and adapt to an ever-changing, open-ended world. A key challenge is ensuring these AI agents are…

Machine Learning · Computer Science 2025-12-10 Mikayel Samvelyan

In dynamic programming and reinforcement learning, the policy for the sequential decision making of an agent in a stochastic environment is usually determined by expressing the goal as a scalar reward function and seeking a policy that…

Artificial Intelligence · Computer Science 2025-02-26 Simon Dima , Simon Fischer , Jobst Heitzig , Joss Oliver

We introduce the first complete formal solution to corrigibility in the off-switch game, with provable guarantees in multi-step, partially observed environments. Our framework consists of five *structurally separate* utility heads --…

Artificial Intelligence · Computer Science 2025-11-20 Aran Nayebi

Alignment research focuses on making individual AI systems reliable. Human institutions achieve reliable collective behaviour differently: they mitigate the risk posed by misaligned individuals through organisational structure. Multi-agent…

Artificial Intelligence · Computer Science 2026-02-17 William Waites

We consider a model of nomadic agents exploring and competing for time-varying location-specific resources, arising in crowdsourced transportation services, online communities, and in traditional location based economic activity. This model…

Computer Science and Game Theory · Computer Science 2016-02-23 Pu Yang , Krishnamurthy Iyer , Peter Frazier
‹ Prev 1 4 5 6 7 8 10 Next ›