English
Related papers

Related papers: Inverse Reward Design

200 papers

We consider the problem of reinforcement learning under safety requirements, in which an agent is trained to complete a given task, typically formalized as the maximization of a reward signal over time, while concurrently avoiding…

Machine Learning · Computer Science 2018-09-25 Tu-Hoa Pham , Giovanni De Magistris , Don Joven Agravante , Subhajit Chaudhury , Asim Munawar , Ryuki Tachibana

Natural language is an intuitive and expressive way to communicate reward information to autonomous agents. It encompasses everything from concrete instructions to abstract descriptions of the world. Despite this, natural language is often…

Artificial Intelligence · Computer Science 2022-04-12 Theodore R. Sumers , Robert D. Hawkins , Mark K. Ho , Thomas L. Griffiths , Dylan Hadfield-Menell

We study the game redesign problem in which an external designer has the ability to change the payoff function in each round, but incurs a design cost for deviating from the original game. The players apply no-regret learning algorithms to…

Computer Science and Game Theory · Computer Science 2021-10-25 Yuzhe Ma , Young Wu , Xiaojin Zhu

Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with reinforcement learning) or reward-free (directly fine-tuning…

Computation and Language · Computer Science 2026-03-03 Ruoxi Cheng , Haoxuan Ma , Weixin Wang , Ranjie Duan , Jiexi Liu , Xiaoshuang Jia , Simeng Qin , Xiaochun Cao , Yang Liu , Xiaojun Jia

Reward engineering and designing an incentive reward function are non-trivial tasks to train agents in complex environments. Furthermore, an inaccurate reward function may lead to a biased behaviour which is far from an efficient and…

Robotics · Computer Science 2021-05-04 Saeed Tafazzol , Erfan Fathi , Mahdi Rezaei , Ehsan Asali

A misspecified reward can degrade sample efficiency and induce undesired behaviors in reinforcement learning (RL) problems. We propose symbolic reward machines for incorporating high-level task knowledge when specifying the reward signals.…

Artificial Intelligence · Computer Science 2022-04-22 Weichao Zhou , Wenchao Li

The gloabal objective of inverse Reinforcement Learning (IRL) is to estimate the unknown cost function of some MDP base on observed trajectories generated by (approximate) optimal policies. The classical approach consists in tuning this…

Machine Learning · Computer Science 2021-05-26 Firas Jarboui , Vianney Perchet

Dynamic mechanism design has garnered significant attention from both computer scientists and economists in recent years. By allowing agents to interact with the seller over multiple rounds, where agents' reward functions may change with…

Machine Learning · Computer Science 2022-06-22 Boxiang Lyu , Zhaoran Wang , Mladen Kolar , Zhuoran Yang

In computational design and fabrication, neural networks are becoming important surrogates for bulky forward simulations. A long-standing, intertwined question is that of inverse design: how to compute a design that satisfies a desired…

Graphics · Computer Science 2022-08-30 Navid Ansari , Hans-Peter Seidel , Vahid Babaei

We provide an original theoretical study of Inverse Reinforcement Learning (IRL) through the lens of reward compatibility, a novel framework to quantify the compatibility of a reward with the given expert's demonstrations. Intuitively, a…

Machine Learning · Computer Science 2025-01-15 Filippo Lazzati , Mirco Mutti , Alberto Metelli

We consider the problem of imitation learning from a finite set of expert trajectories, without access to reinforcement signals. The classical approach of extracting the expert's reward function via inverse reinforcement learning, followed…

Machine Learning · Computer Science 2019-06-10 Ruohan Wang , Carlo Ciliberto , Pierluigi Amadori , Yiannis Demiris

Estimating the unknown reward functions driving agents' behaviors is of central interest in inverse reinforcement learning and game theory. To tackle this problem, we develop a unified framework for reward function recovery in two-player…

Machine Learning · Computer Science 2026-05-20 Junyi Liao , Zihan Zhu , Ethan Fang , Zhuoran Yang , Vahid Tarokh

We propose an inverse reinforcement learning (IRL) approach using Deep Q-Networks to extract the rewards in problems with large state spaces. We evaluate the performance of this approach in a simulation-based autonomous driving scenario.…

Artificial Intelligence · Computer Science 2017-09-22 Sahand Sharifzadeh , Ioannis Chiotellis , Rudolph Triebel , Daniel Cremers

If capable AI agents are generally incentivized to seek power in service of the objectives we specify for them, then these systems will pose enormous risks, in addition to enormous benefits. In fully observable environments, most reward…

Artificial Intelligence · Computer Science 2022-10-13 Alexander Matt Turner , Prasad Tadepalli

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

When training artificial intelligence (AI) to perform tasks, humans often care not only about whether a task is completed but also how it is performed. As AI agents tackle increasingly complex tasks, aligning their behavior with…

Artificial Intelligence · Computer Science 2026-02-24 Zhiqin Qian , Ryan Diaz , Sangwon Seo , Vaibhav Unhelkar

To regulate a social system comprised of self-interested agents, economic incentives are often required to induce a desirable outcome. This incentive design problem naturally possesses a bilevel structure, in which a designer modifies the…

Computer Science and Game Theory · Computer Science 2022-10-14 Boyi Liu , Jiayang Li , Zhuoran Yang , Hoi-To Wai , Mingyi Hong , Yu Marco Nie , Zhaoran Wang

Complex behaviors are often driven by an internal model, which integrates sensory information over time and facilitates long-term planning. Inferring an agent's internal model is a crucial ingredient in social interactions (theory of mind),…

Machine Learning · Computer Science 2019-06-13 Zhengwei Wu , Paul Schrater , Xaq Pitkow

Large language models (LLMs) trained with Reinforcement Learning from Human Feedback (RLHF) have demonstrated remarkable capabilities, but their underlying reward functions and decision-making processes remain opaque. This paper introduces…

Computation and Language · Computer Science 2025-10-07 Jared Joselowitz , Ritam Majumdar , Arjun Jagota , Matthieu Bou , Nyal Patel , Satyapriya Krishna , Sonali Parbhoo

For many reinforcement learning (RL) applications, specifying a reward is difficult. This paper considers an RL setting where the agent obtains information about the reward only by querying an expert that can, for example, evaluate…

Machine Learning · Computer Science 2022-02-01 David Lindner , Matteo Turchetta , Sebastian Tschiatschek , Kamil Ciosek , Andreas Krause