中文
相关论文

相关论文: Contrastive Explanations for Comparing Preferences…

200 篇论文

Reinforcement learning (RL) requires access to a reward function that incentivizes the right behavior, but these are notoriously hard to specify for complex tasks. Preference-based RL provides an alternative: learning policies using a…

机器学习 · 计算机科学 2021-11-05 Kimin Lee , Laura Smith , Anca Dragan , Pieter Abbeel

Advances in multi-agent reinforcement learning (MARL) enable sequential decision making for a range of exciting multi-agent applications such as cooperative AI and autonomous driving. Explaining agent decisions is crucial for improving…

人工智能 · 计算机科学 2022-05-24 Kayla Boggess , Sarit Kraus , Lu Feng

Reinforcement learning (RL) algorithms find applications in inventory control, recommender systems, vehicular traffic management, cloud computing and robotics. The real-world complications of many tasks arising in these domains makes them…

机器学习 · 计算机科学 2021-06-03 Sindhu Padakandla

Reinforcement learning (RL) agents need to be robust to variations in safety-critical environments. While system identification methods provide a way to infer the variation from online experience, they can fail in settings where fast…

机器学习 · 计算机科学 2022-03-07 Annie Xie , Shagun Sodhani , Chelsea Finn , Joelle Pineau , Amy Zhang

A characteristic of reinforcement learning is the ability to develop unforeseen strategies when solving problems. While such strategies sometimes yield superior performance, they may also result in undesired or even dangerous behavior. In…

In many real-world applications, reinforcement learning (RL) agents might have to solve multiple tasks, each one typically modeled via a reward function. If reward functions are expressed linearly, and the agent has previously learned a set…

机器学习 · 计算机科学 2022-06-24 Lucas N. Alegre , Ana L. C. Bazzan , Bruno C. da Silva

Preference-based reinforcement learning (RL) provides a framework to train agents using human preferences between two behaviors. However, preference-based RL has been challenging to scale since it requires a large amount of human feedback…

机器学习 · 计算机科学 2023-03-03 Changyeon Kim , Jongjin Park , Jinwoo Shin , Honglak Lee , Pieter Abbeel , Kimin Lee

Inverse reinforcement learning (IRL) addresses the problem of recovering a task description given a demonstration of the optimal policy used to solve such a task. The optimal policy is usually provided by an expert or teacher, making IRL…

机器学习 · 计算机科学 2012-02-09 Héctor Ratia , Luis Montesano , Ruben Martinez-Cantin

Deep Reinforcement Learning (RL) is mainly studied in a setting where the training and the testing environments are similar. But in many practical applications, these environments may differ. For instance, in control systems, the robot(s)…

机器学习 · 计算机科学 2022-10-25 Jean-Baptiste Gaya , Laure Soulier , Ludovic Denoyer

In standard reinforcement learning (RL), a learning agent seeks to optimize the overall reward. However, many key aspects of a desired behavior are more naturally expressed as constraints. For instance, the designer may want to limit the…

机器学习 · 计算机科学 2021-01-29 Sobhan Miryoosefi , Kianté Brantley , Hal Daumé , Miroslav Dudik , Robert Schapire

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…

机器学习 · 计算机科学 2024-10-10 Julian Dierkes , Emma Cramer , Holger H. Hoos , Sebastian Trimpe

Learning auxiliary tasks, such as multiple predictions about the world, can provide many benefits to reinforcement learning systems. A variety of off-policy learning algorithms have been developed to learn such predictions, but as yet there…

Reinforcement learning (RL) has achieved tremendous success as a general framework for learning how to make decisions. However, this success relies on the interactive hand-tuning of a reward function by RL experts. On the other hand,…

机器学习 · 计算机科学 2020-11-24 Letian Chen , Rohan Paleja , Muyleng Ghuy , Matthew Gombolay

Can humans get arbitrarily capable reinforcement learning (RL) agents to do their bidding? Or will sufficiently capable RL agents always find ways to bypass their intended objectives by shortcutting their reward signal? This question…

人工智能 · 计算机科学 2021-03-29 Tom Everitt , Marcus Hutter , Ramana Kumar , Victoria Krakovna

Why do reinforcement learning (RL) policies fail or succeed? This is a challenging question due to the complex, high-dimensional nature of agent-environment interactions. In this work, we take a causal perspective on explaining the behavior…

机器学习 · 统计学 2025-07-22 Armin Kekić , Jan Schneider , Dieter Büchler , Bernhard Schölkopf , Michel Besserve

In preference-based reinforcement learning (PbRL), a reward function is learned from a type of human feedback called preference. To expedite preference collection, recent works have leveraged \emph{offline preferences}, which are…

机器学习 · 计算机科学 2024-03-18 Guoxi Zhang , Han Bao , Hisashi Kashima

Reinforcement learning (RL) algorithms assume that users specify tasks by manually writing down a reward function. However, this process can be laborious and demands considerable technical expertise. Can we devise RL algorithms that instead…

机器学习 · 计算机科学 2022-01-03 Benjamin Eysenbach , Sergey Levine , Ruslan Salakhutdinov

Autonomous assistance of people with motor impairments is one of the most promising applications of autonomous robotic systems. Recent studies have reported encouraging results using deep reinforcement learning (RL) in the healthcare…

机器人学 · 计算机科学 2024-04-02 Takayuki Osa , Tatsuya Harada

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…

Reliable real-world deployment of reinforcement learning (RL) methods requires a nuanced understanding of their strengths and weaknesses and how they compare to those of humans. Human-machine systems are becoming more prevalent and the…

人工智能 · 计算机科学 2024-05-21 Eric Pulick , Vladimir Menkov , Yonatan Mintz , Paul Kantor , Vicki Bier