Results 251 to 260 of about 34,803,504 (287)

The Digital Transformation of Rehabilitation Medicine: A Narrative Review of Artificial Intelligence Innovations, Clinical Integration, and Future Paradigms. [PDF]

J Eval Clin Pract
Wu H, Yang Y, Wang L, Su H, Li X.
europepmc   +1 more source

Multi-Property De Novo Drug Design Using Deep Learning-Based Knowledge Distillation and Reinforcement Learning. [PDF]

Int J Mol Sci
Wang L, Lu Z, Cui L, Liu C, Qin Y, Feng S, Wang D, Yin W, Kang Z, Cao L.   +9 more
europepmc   +1 more source

SymCART: a symbiotic cognitive-affective reinforcement transformer for optimizing educational interventions. [PDF]

Front Psychol
Liu D, Li F, Lu D, Yu W, Jiao R.
europepmc   +1 more source

Modeling network evolution by multi-agent reinforcement learning. [PDF]

Nat Commun
Li D, Lin T, Bao Z, Gu B, Zhang Y, Yang F, Sun Y, Du Z, Holme P.   +8 more
europepmc   +1 more source

Some of the next articles are maybe not open access.

Related searches:

Model-based reinforcement learning with dimension reduction

Neural Networks, 2016
The goal of reinforcement learning is to learn an optimal policy which controls an agent to acquire the maximum cumulative reward. The model-based reinforcement learning approach learns a transition model of the environment from data, and then derives the optimal policy using the transition model.
Masashi Sugiyama, Morimoto Jun, Voot Tangkaratt   +2 more
exaly   +3 more sources

Multiple Model-Based Reinforcement Learning

Neural Computation, 2002
We propose a modular reinforcement learning architecture for nonlinear, nonstationary control tasks, which we call multiple model-based reinforcement learning (MMRL). The basic idea is to decompose a complex task into multiple domains in space and time based on the predictability of the environmental dynamics.
Kenji Doya, Kazuyuki Samejima, Ken-ichi Katagiri, Mitsuo Kawato   +3 more
openaire   +3 more sources

Fuzzy Model-Based Reinforcement Learning

2002
Model-based reinforcement learning methods are known to be highly efficient with respect to the number of trials required for learning optimal policies. In this article a novel fuzzy model-based reinforcement learning approach, fuzzy prioritized sweeping (F-PS), is presented.
Martin Appl, Wilfried Brauer
openaire   +2 more sources

Learning exploration strategies in model-based reinforcement learning

International Joint Conference on Autonomous Agents and Multiagent Systems, 2013
Reinforcement learning (RL) is a paradigm for learning sequential decision making tasks. However, typically the user must hand-tune exploration parameters for each different domain and/or algorithm that they are using. In this work, we present an algorithm called LEO for learning these exploration strategies on-line.
Hester, Todd, Stone, Peter, Lopes, Manuel   +2 more
openaire   +3 more sources

Importance sampling for model-based reinforcement learning

2012 20th Signal Processing and Communications Applications Conference (SIU), 2012
Most of the state-of-the-art reinforcement learning algorithms are based on Bellman equations and make use of fixed-point iteration methods to converge to suboptimal solutions. However, some of the recent approaches transform the reinforcement learning problem into an equivalent likelihood maximization problem with using appropriate graphical models ...
Orhan Sonmez, Ali Taylan Cemgil
openaire   +2 more sources