English
Related papers

Related papers: Penalizing side effects using stepwise relative re…

200 papers

Regression adjustments are often considered by investigators to improve the estimation efficiency of causal effect in randomized experiments when there exists many pre-experiment covariates. In this paper, we provide conditions that…

Statistics Theory · Mathematics 2018-09-25 Hanzhong Liu , Yuehan Yang

Autonomous agents optimize the reward function we give them. What they don't know is how hard it is for us to design a reward function that actually captures what we want. When designing the reward, we might think of some specific training…

Artificial Intelligence · Computer Science 2020-10-08 Dylan Hadfield-Menell , Smitha Milli , Pieter Abbeel , Stuart Russell , Anca Dragan

We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As a victim, we consider RL agents whose objective is to find…

Machine Learning · Computer Science 2020-11-24 Amin Rakhsha , Goran Radanovic , Rati Devidze , Xiaojin Zhu , Adish Singla

Behavior cloning of expert demonstrations can speed up learning optimal policies in a more sample-efficient way over reinforcement learning. However, the policy cannot extrapolate well to unseen states outside of the demonstration data,…

Machine Learning · Computer Science 2022-10-19 Jung Yeon Park , Lawson L. S. Wong

Offline reinforcement learning enables agents to leverage large pre-collected datasets of environment transitions to learn control policies, circumventing the need for potentially expensive or unsafe online data collection. Significant…

Machine Learning · Computer Science 2022-03-17 Cong Lu , Philip J. Ball , Jack Parker-Holder , Michael A. Osborne , Stephen J. Roberts

Learning a reward function from demonstrations suffers from low sample-efficiency. Even with abundant data, current inverse reinforcement learning methods that focus on learning from a single environment can fail to handle slight changes in…

Machine Learning · Computer Science 2024-05-15 Thomas Kleine Buening , Victor Villin , Christos Dimitrakakis

Reachability analysis, in general, is a fundamental method that supports formally-correct synthesis, robust model predictive control, set-based observers, fault detection, invariant computation, and conformance checking, to name but a few.…

Systems and Control · Electrical Eng. & Systems 2020-11-17 Niklas Kochdumper , Bastian Schürmann , Matthias Althoff

The cost of error in many high-stakes settings is asymmetric: misdiagnosing pneumonia when absent is an inconvenience, but failing to detect it when present can be life-threatening. Because of this, artificial intelligence (AI) models used…

General Economics · Economics 2025-11-12 David Autor , Andrew Caplin , Daniel Martin , Philip Marx

We study AI alignment through the lens of law-and-economics models of deterrence and enforcement. In these models, misconduct is not treated as an external failure, but as a strategic response to incentives: an actor weighs the gain from…

Machine Learning · Computer Science 2026-05-12 Rohit Agarwal , Joshua Lin , Mark Braverman , Elad Hazan

We develop a framework for interacting with uncertain environments in reinforcement learning (RL) by leveraging preferences in the form of utility functions. We claim that there is value in considering different risk measures during…

Machine Learning · Computer Science 2021-02-23 Hannes Eriksson , Christos Dimitrakakis

Discontinuities can be fairly arbitrary but also cause a significant impact on outcomes in larger systems. Indeed, their arbitrariness is why they have been used to infer causal relationships among variables in numerous settings. Regression…

Information Theory · Computer Science 2023-12-29 Ibtihal Ferwana , Suyoung Park , Ting-Yi Wu , Lav R. Varshney

There has been significant progress in deep reinforcement learning (RL) in recent years. Nevertheless, finding suitable hyperparameter configurations and reward functions remains challenging even for experts, and performance heavily relies…

Machine Learning · Computer Science 2024-10-10 Julian Dierkes , Emma Cramer , Holger H. Hoos , Sebastian Trimpe

As reinforcement learning agents become increasingly integrated into complex, real-world environments, designing for safety becomes a critical consideration. We specifically focus on researching scenarios where agents can cause undesired…

Machine Learning · Computer Science 2020-10-07 Santiago Miret , Somdeb Majumdar , Carroll Wainwright

In many scenarios, a principal dynamically interacts with an agent and offers a sequence of incentives to align the agent's behavior with a desired objective. This paper focuses on the problem of synthesizing an incentive sequence that,…

Optimization and Control · Mathematics 2020-07-20 Yagiz Savas , Vijay Gupta , Ufuk Topcu

While enforcing egalitarian social norms is critical for human society, punishing social norm violators often incurs a cost to the self. This cost looms even larger when one can benefit from an unequal distribution of resources (i.e.…

Neurons and Cognition · Quantitative Biology 2025-07-29 Shen Zhang , Oriel FeldmanHall , Sébastien Hétu , A. Ross Otto

Policies trained via reinforcement learning (RL) are often very complex even for simple tasks. In an episode with $n$ time steps, a policy will make $n$ decisions on actions to take, many of which may appear non-intuitive to the observer.…

Artificial Intelligence · Computer Science 2021-11-17 Daniel McNamee , Hana Chockler

Reinforcement learning algorithms typically necessitate extensive exploration of the state space to find optimal policies. However, in safety-critical applications, the risks associated with such exploration can lead to catastrophic…

Machine Learning · Computer Science 2025-02-28 Kaustubh Mani , Vincent Mai , Charlie Gauthier , Annie Chen , Samer Nashed , Liam Paull

Finding meaningful and accurate dense rewards is a fundamental task in the field of reinforcement learning (RL) that enables agents to explore environments more efficiently. In traditional RL settings, agents learn optimal policies through…

Artificial Intelligence · Computer Science 2025-12-05 Shuyuan Zhang

In reinforcement learning, a decision needs to be made at some point as to whether it is worthwhile to carry on with the learning process or to terminate it. In many such situations, stochastic elements are often present which govern the…

Machine Learning · Computer Science 2019-02-13 Nikki Lijing Kuang , Clement H. C. Leung

Safety controllers is widely used to achieve safe reinforcement learning. Most methods that apply a safety controller are using handcrafted safety constraints to construct the safety controller. However, when the environment dynamics are…

Artificial Intelligence · Computer Science 2023-09-22 Haoyu Wang , Xin Yuan , Qinqing Ren