中文
相关论文

相关论文: Learning values across many orders of magnitude

200 篇论文

Reinforcement learning (RL) is a central problem in artificial intelligence. This problem consists of defining artificial agents that can learn optimal behaviour by interacting with an environment -- where the optimal behaviour is defined…

Many learning algorithms are known to converge to an equilibrium for specific classes of games if the same learning algorithm is adopted by all agents. However, when the agents are self-interested, a natural question is whether agents have…

计算机科学与博弈论 · 计算机科学 2024-02-15 Shivam Bajaj , Pranoy Das , Yevgeniy Vorobeychik , Vijay Gupta

How can we build AI systems that can learn any set of individual human values both quickly and safely, avoiding causing harm or violating societal standards for acceptable behavior during the learning process? We explore the effects of…

人工智能 · 计算机科学 2024-11-11 Andrea Wynn , Ilia Sucholutsky , Thomas L. Griffiths

While recent progress has spawned very powerful machine learning systems, those agents remain extremely specialized and fail to transfer the knowledge they gain to similar yet unseen tasks. In this paper, we study a simple reinforcement…

机器学习 · 计算机科学 2020-12-15 Remi Tachet , Philip Bachman , Harm van Seijen

As application demands for online convex optimization accelerate, the need for designing new methods that simultaneously cover a large class of convex functions and impose the lowest possible regret is highly rising. Known online…

机器学习 · 计算机科学 2019-06-04 Saeed Masoudian , Ali Arabzadeh , Mahdi Jafari Siavoshani , Milad Jalal , Alireza Amouzad

An algorithm is said to be adaptive to a certain parameter (of the problem) if it does not need a priori knowledge of such a parameter but performs competitively to those that know it. This dissertation presents our work on adaptive…

机器学习 · 计算机科学 2023-07-10 Zhenxun Zhuang

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

Reinforcement learning (RL) algorithms update an agent's parameters according to one of several possible rules, discovered manually through years of research. Automating the discovery of update rules from data could lead to more efficient…

In the future, artificial learning agents are likely to become increasingly widespread in our society. They will interact with both other learning agents and humans in a variety of complex settings including social dilemmas. We consider the…

计算机科学与博弈论 · 计算机科学 2019-11-21 Tobias Baumann , Thore Graepel , John Shawe-Taylor

Discounted reinforcement learning is fundamentally incompatible with function approximation for control in continuing tasks. It is not an optimization problem in its usual formulation, so when using function approximation there is no…

人工智能 · 计算机科学 2019-11-28 Abhishek Naik , Roshan Shariff , Niko Yasui , Hengshuai Yao , Richard S. Sutton

Learning to control an environment without hand-crafted rewards or expert data remains challenging and is at the frontier of reinforcement learning research. We present an unsupervised learning algorithm to train agents to achieve…

机器学习 · 计算机科学 2018-11-29 David Warde-Farley , Tom Van de Wiele , Tejas Kulkarni , Catalin Ionescu , Steven Hansen , Volodymyr Mnih

Observing a human demonstrator manipulate objects provides a rich, scalable and inexpensive source of data for learning robotic policies. However, transferring skills from human videos to a robotic manipulator poses several challenges, not…

机器人学 · 计算机科学 2023-03-08 Minttu Alakuijala , Gabriel Dulac-Arnold , Julien Mairal , Jean Ponce , Cordelia Schmid

Inverse Reinforcement Learning (IRL) aims to facilitate a learner's ability to imitate expert behavior by acquiring reward functions that explain the expert's decisions. Regularized IRL applies strongly convex regularizers to the learner's…

机器学习 · 计算机科学 2020-12-04 Wonseok Jeon , Chen-Yang Su , Paul Barde , Thang Doan , Derek Nowrouzezahrai , Joelle Pineau

Deep reinforcement learning (RL) algorithms can learn complex policies to optimize agent operation over time. RL algorithms have shown promising results in solving complicated problems in recent years. However, their application on…

机器学习 · 计算机科学 2021-09-29 Hamed Khorasgani , Haiyan Wang , Chetan Gupta , Susumu Serita

Potential-based reward shaping provides an approach for designing good reward functions, with the purpose of speeding up learning. However, automatically finding potential functions for complex environments is a difficult problem (in fact,…

机器学习 · 计算机科学 2021-02-22 Martin Klissarov , Doina Precup

Several applications of Reinforcement Learning suffer from instability due to high variance. This is especially prevalent in high dimensional domains. Regularization is a commonly used technique in machine learning to reduce variance, at…

机器学习 · 计算机科学 2019-04-12 Pierre Thodoroff , Audrey Durand , Joelle Pineau , Doina Precup

Reinforcement learning agents learn from rewards, but humans can uniquely assign value to novel, abstract outcomes in a goal-dependent manner. However, this flexibility is cognitively costly, making learning less efficient. Here, we propose…

神经元与认知 · 定量生物学 2025-09-11 Gaia Molinaro , Anne G. E. Collins

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…

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

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