中文
相关论文

相关论文: Contrastive Explanations for Comparing Preferences…

200 篇论文

Reinforcement learning (RL) agents optimize only the features specified in a reward function and are indifferent to anything left out inadvertently. This means that we must not only specify what to do, but also the much larger space of what…

机器学习 · 计算机科学 2019-04-22 Rohin Shah , Dmitrii Krasheninnikov , Jordan Alexander , Pieter Abbeel , Anca Dragan

An internet network service provider manages its network with multiple objectives, such as high quality of service (QoS) and minimum computing resource usage. To achieve these objectives, a reinforcement learning-based (RL) algorithm has…

网络与互联网体系结构 · 计算机科学 2025-06-17 DongNyeong Heo , Daniela Noemi Rim , Heeyoul Choi

Reinforcement learning~(RL) is a versatile framework for learning to solve complex real-world tasks. However, influences on the learning performance of RL algorithms are often poorly understood in practice. We discuss different analysis…

机器学习 · 计算机科学 2023-09-14 Jan Schneider , Pierre Schumacher , Daniel Häufle , Bernhard Schölkopf , Dieter Büchler

Conveying complex objectives to reinforcement learning (RL) agents can often be difficult, involving meticulous design of reward functions that are sufficiently informative yet easy enough to provide. Human-in-the-loop RL methods allow…

机器学习 · 计算机科学 2021-06-10 Kimin Lee , Laura Smith , Pieter Abbeel

One of the challenges in applying reinforcement learning in a complex real-world environment lies in providing the agent with a sufficiently detailed reward function. Any misalignment between the reward and the desired behavior can result…

机器学习 · 计算机科学 2025-10-24 Neta Glazer , Aviv Navon , Aviv Shamsian , Ethan Fetaya

Designing reward functions for efficiently guiding reinforcement learning (RL) agents toward specific behaviors is a complex task. This is challenging since it requires the identification of reward structures that are not sparse and that…

机器学习 · 计算机科学 2023-11-01 Dhawal Gupta , Yash Chandak , Scott M. Jordan , Philip S. Thomas , Bruno Castro da Silva

As the operations of autonomous systems generally affect simultaneously several users, it is crucial that their designs account for fairness considerations. In contrast to standard (deep) reinforcement learning (RL), we investigate the…

人工智能 · 计算机科学 2020-08-19 Umer Siddique , Paul Weng , Matthieu Zimmer

An ambitious goal for machine learning is to create agents that behave ethically: The capacity to abide by human moral norms would greatly expand the context in which autonomous agents could be practically and safely deployed, e.g. fully…

人工智能 · 计算机科学 2021-07-21 Adrien Ecoffet , Joel Lehman

Learning a reward function from human preferences is challenging as it typically requires having a high-fidelity simulator or using expensive and potentially unsafe actual physical rollouts in the environment. However, in many tasks the…

机器学习 · 计算机科学 2022-02-18 Daniel Shin , Daniel S. Brown , Anca D. Dragan

Reinforcement Learning (RL) methods have emerged as a popular choice for training an efficient and effective dialogue policy. However, these methods suffer from sparse and unstable reward signals returned by a user simulator only when a…

人工智能 · 计算机科学 2020-09-18 Ziming Li , Sungjin Lee , Baolin Peng , Jinchao Li , Julia Kiseleva , Maarten de Rijke , Shahin Shayandeh , Jianfeng Gao

In some agent designs like inverse reinforcement learning an agent needs to learn its own reward function. Learning the reward function and optimising for it are typically two different processes, usually performed at different stages. We…

人工智能 · 计算机科学 2020-04-29 Stuart Armstrong , Jan Leike , Laurent Orseau , Shane Legg

Reinforcement learning agents tend to develop habits that are effective only under specific policies. Following an initial exploration phase where agents try out different actions, they eventually converge onto a particular policy. As this…

机器学习 · 计算机科学 2024-06-25 Miguel Suau , Matthijs T. J. Spaan , Frans A. Oliehoek

Meta reinforcement learning (meta-RL) aims to learn a policy solving a set of training tasks simultaneously and quickly adapting to new tasks. It requires massive amounts of data drawn from training tasks to infer the common structure…

机器学习 · 计算机科学 2022-07-21 Yijie Guo , Qiucheng Wu , Honglak Lee

The objective of a reinforcement learning agent is to discover better actions through exploration. However, typical exploration techniques aim to maximize rewards, often incurring high costs in both exploration and learning processes. We…

机器学习 · 计算机科学 2024-12-24 Akane Tsuboya , Yu Kono , Tatsuji Takahashi

Reinforcement learning algorithms describe how an agent can learn an optimal action policy in a sequential decision process, through repeated experience. In a given environment, the agent policy provides him some running and terminal…

理论经济学 · 经济学 2020-03-24 Arthur Charpentier , Romuald Elie , Carl Remlinger

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.…

人工智能 · 计算机科学 2021-11-17 Daniel McNamee , Hana Chockler

Learning-based approaches for solving large sequential decision making problems have become popular in recent years. The resulting agents perform differently and their characteristics depend on those of the underlying learning approach.…

机器学习 · 计算机科学 2020-08-04 Timo P. Gros , Daniel Höller , Jörg Hoffmann , Verena Wolf

Some researchers speculate that intelligent reinforcement learning (RL) agents would be incentivized to seek resources and power in pursuit of their objectives. Other researchers point out that RL agents need not have human-like…

人工智能 · 计算机科学 2023-01-31 Alexander Matt Turner , Logan Smith , Rohin Shah , Andrew Critch , Prasad Tadepalli

Non-uniform goal selection has the potential to improve the reinforcement learning (RL) of skills over uniform-random selection. In this paper, we introduce a method for learning a goal-selection policy in intrinsically-motivated…

人工智能 · 计算机科学 2024-11-07 Erik M. Lintunen , Nadia M. Ady , Christian Guckelsberger

Learning policies via preference-based reward learning is an increasingly popular method for customizing agent behavior, but has been shown anecdotally to be prone to spurious correlations and reward hacking behaviors. While much prior work…

机器学习 · 计算机科学 2023-03-21 Jeremy Tien , Jerry Zhi-Yang He , Zackory Erickson , Anca D. Dragan , Daniel S. Brown