Results 1 to 10 of about 5,876,040 (331)
Reinforcement Learning: A Survey [PDF]
Journal of Artificial Intelligence Research, 1996 This paper surveys the field of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning.
Kaelbling, L. P. +2 more
core +14 more sources
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback [PDF]
arXiv.org, 2022 We apply preference modeling and reinforcement learning from human feedback (RLHF) to finetune language models to act as helpful and harmless assistants.
Yuntao Bai +30 more
semanticscholar +1 more source
Training Diffusion Models with Reinforcement Learning [PDF]
International Conference on Learning Representations, 2023 Diffusion models are a class of flexible generative models trained with an approximation to the log-likelihood objective. However, most use cases of diffusion models are not concerned with likelihoods, but instead with downstream objectives such as human-
Kevin Black +4 more
semanticscholar +1 more source
Efficient Online Reinforcement Learning with Offline Data [PDF]
International Conference on Machine Learning, 2023 Sample efficiency and exploration remain major challenges in online reinforcement learning (RL). A powerful approach that can be applied to address these issues is the inclusion of offline data, such as prior trajectories from a human expert or a sub ...
Philip J. Ball +3 more
semanticscholar +1 more source
IEEE Access, 2021 A well-designed demand response (DR) program is essential in smart home to optimize energy usage according to user preferences. In this study, we proposed a multiobjective reinforcement learning (MORL) algorithm to design a DR program.
Song-Jen Chen, Wei-Yu Chiu, Wei-Jen Liu
doaj +1 more source
Learning an Accurate State Transition Dynamics Model by Fitting Both a Function and its Derivative
IEEE Access, 2022 Learning accurate state transition dynamics model in a sample-efficient way is important to predict the future states from the current states and actions of a system both accurately and efficiently in model-based reinforcement learning for many robotic ...
Youngho Kim, Hoosang Lee, Jeha Ryu
doaj +1 more source
Guiding Pretraining in Reinforcement Learning with Large Language Models [PDF]
International Conference on Machine Learning, 2023 Reinforcement learning algorithms typically struggle in the absence of a dense, well-shaped reward function. Intrinsically motivated exploration methods address this limitation by rewarding agents for visiting novel states or transitions, but these ...
Yuqing Du +7 more
semanticscholar +1 more source
IEEE Access, 2022 Snake-like modular robots (MRs) are highly flexible, but, to traverse a challenging terrain or explore a region of interest, MR needs to attain efficient locomotion depending on a tradeoff between objectives like forward velocity and power consumption of
Akash Singh +3 more
doaj +1 more source
Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning [PDF]
International Conference on Learning Representations, 2022 Offline reinforcement learning (RL), which aims to learn an optimal policy using a previously collected static dataset, is an important paradigm of RL.
Zhendong Wang +2 more
semanticscholar +1 more source
Frontiers in Psychiatry, 2023 IntroductionMany American employers seek to alleviate employee mental health symptoms through resources like employee assistance programs (EAPs), yet these programs are often underutilized.
Ashley B. West +4 more
doaj +1 more source