English
Related papers

Related papers: Imperfect World Models are Exploitable

200 papers

The Exploration-Exploitation tradeoff arises in Reinforcement Learning when one cannot tell if a policy is optimal. Then, there is a constant need to explore new actions instead of exploiting past experience. In practice, it is common to…

Machine Learning · Computer Science 2019-09-10 Lior Shani , Yonathan Efroni , Shie Mannor

We tackle the problem of policy learning from expert demonstrations without a reward function. A central challenge in this space is that these policies fail upon deployment due to issues of distributional shift, environment stochasticity,…

Machine Learning · Computer Science 2024-08-19 Victor Kolev , Rafael Rafailov , Kyle Hatch , Jiajun Wu , Chelsea Finn

Reinforcement Learning (RL) applications in real-world scenarios must prioritize safety and reliability, which impose strict constraints on agent behavior. Model-based RL leverages predictive world models for action planning and policy…

Artificial Intelligence · Computer Science 2025-06-06 Artem Latyshev , Gregory Gorbov , Aleksandr I. Panov

Reward models play a key role in aligning language model applications towards human preferences. However, this setup creates an incentive for the language model to exploit errors in the reward model to achieve high estimated reward, a…

In this paper, we introduce the notion of replicable policies in the context of stochastic bandits, one of the canonical problems in interactive learning. A policy in the bandit environment is called replicable if it pulls, with high…

Machine Learning · Computer Science 2023-02-16 Hossein Esfandiari , Alkis Kalavasis , Amin Karbasi , Andreas Krause , Vahab Mirrokni , Grigoris Velegkas

Social networks are frequently polluted by rumors, which can be detected by advanced models such as graph neural networks. However, the models are vulnerable to attacks and understanding the vulnerabilities is critical to rumor detection in…

Machine Learning · Computer Science 2022-10-17 Yuefei Lyu , Xiaoyu Yang , Jiaxin Liu , Philip S. Yu , Sihong Xie , Xi Zhang

We integrate information-theoretic concepts into the design and analysis of optimistic algorithms and Thompson sampling. By making a connection between information-theoretic quantities and confidence bounds, we obtain results that relate…

Machine Learning · Statistics 2019-11-25 Xiuyuan Lu , Benjamin Van Roy

In contemporary society, the effective utilization of public resources remains a subject of significant concern. A common issue arises from defectors seeking to obtain an excessive share of these resources for personal gain, potentially…

Dynamical Systems · Mathematics 2024-04-02 Lichen Wang , Yuyuan Liu , Ruqiang Guo , Liang Zhang , Linjie Liu , Shijia Hua

Reward hacking--where agents exploit flaws in imperfect reward functions rather than performing tasks as intended--poses risks for AI alignment. Reward hacking has been observed in real training runs, with coding agents learning to…

Artificial Intelligence · Computer Science 2025-08-26 Mia Taylor , James Chua , Jan Betley , Johannes Treutlein , Owain Evans

Meta-Reinforcement learning approaches aim to develop learning procedures that can adapt quickly to a distribution of tasks with the help of a few examples. Developing efficient exploration strategies capable of finding the most useful…

Machine Learning · Computer Science 2019-11-12 Swaminathan Gurumurthy , Sumit Kumar , Katia Sycara

A task of interest in machine learning (ML) is that of ascribing explanations to the predictions made by ML models. Furthermore, in domains deemed high risk, the rigor of explanations is paramount. Indeed, incorrect explanations can and…

Artificial Intelligence · Computer Science 2025-07-11 Mohamed Siala , Jordi Planes , Joao Marques-Silva

The exploration-exploitation trade-off is central to the description of adaptive behaviour in fields ranging from machine learning, to biology, to economics. While many approaches have been taken, one approach to solving this trade-off has…

Machine Learning · Computer Science 2021-11-29 Beren Millidge , Anil Seth , Christopher Buckley

Decision theory has become widely accepted in the AI community as a useful framework for planning and decision making. Applying the framework typically requires elicitation of some form of probability and utility information. While much…

Artificial Intelligence · Computer Science 2013-02-08 Vu A. Ha , Peter Haddawy

Much of model-based reinforcement learning involves learning a model of an agent's world, and training an agent to leverage this model to perform a task more efficiently. While these models are demonstrably useful for agents, every…

Neural and Evolutionary Computing · Computer Science 2019-11-01 C. Daniel Freeman , Luke Metz , David Ha

Interpretability is often pointed out as a key requirement for trustworthy machine learning. However, learning and releasing models that are inherently interpretable leaks information regarding the underlying training data. As such…

Artificial Intelligence · Computer Science 2024-04-04 Julien Ferry , Ulrich Aïvodji , Sébastien Gambs , Marie-José Huguet , Mohamed Siala

Machine learning models were shown to be vulnerable to model stealing attacks, which lead to intellectual property infringement. Among other methods, substitute model training is an all-encompassing attack applicable to any machine learning…

Machine Learning · Computer Science 2025-03-11 Daryna Oliynyk , Rudolf Mayer , Andreas Rauber

The objective of a reinforcement learning agent is to behave so as to maximise the sum of a suitable scalar function of state: the reward. These rewards are typically given and immutable. In this paper, we instead consider the proposition…

Artificial Intelligence · Computer Science 2020-08-25 Zeyu Zheng , Junhyuk Oh , Matteo Hessel , Zhongwen Xu , Manuel Kroiss , Hado van Hasselt , David Silver , Satinder Singh

A reinforcement learning agent tries to maximize its cumulative payoff by interacting in an unknown environment. It is important for the agent to explore suboptimal actions as well as to pick actions with highest known rewards. Yet, in…

Machine Learning · Computer Science 2019-01-23 Reazul Hasan Russel

We study the problem of choosing optimal policy rules in uncertain environments using models that may be incomplete and/or partially identified. We consider a policymaker who wishes to choose a policy to maximize a particular counterfactual…

Econometrics · Economics 2020-12-22 Thomas M. Russell

Faithful explanations are essential for machine learning models in high-stakes applications. Inherently interpretable models are well-suited for these applications because they naturally provide faithful explanations by revealing their…

Machine Learning · Computer Science 2025-02-28 Chudi Zhong , Panyu Chen , Cynthia Rudin