Results 21 to 30 of about 34,803,504 (287)
Parallel model-based and model-free reinforcement learning for card sorting performance
Scientific Reports, 2020 The Wisconsin Card Sorting Test (WCST) is considered a gold standard for the assessment of cognitive flexibility. On the WCST, repeating a sorting category following negative feedback is typically treated as indicating reduced cognitive flexibility ...
Alexander Steinke +2 more
doaj +1 more source
Model-Based Reinforcement Learning for Atari
CoRR, 2019 Model-free reinforcement learning (RL) can be used to learn effective policies for complex tasks, such as Atari games, even from image observations. However, this typically requires very large amounts of interaction -- substantially more, in fact, than a human would need to learn the same games. How can people learn so quickly?
Lukasz Kaiser +13 more
openaire +5 more sources
Model-Based Reinforcement Learning via Stochastic Hybrid Models
IEEE Open Journal of Control Systems, 2023 Optimal control of general nonlinear systems is a central challenge in automation. Enabled by powerful function approximators, data-driven approaches to control have recently successfully tackled challenging applications.
Hany Abdulsamad, Jan Peters
doaj +1 more source
Reinforcement learning in populations of spiking neurons [PDF]
, 2008 Population coding is widely regarded as a key mechanism for achieving reliable behavioral responses in the face of neuronal variability. But in standard reinforcement learning a flip-side becomes apparent.
Urbanczik, R +3 more
core +1 more source
Tongxin xuebao, 2023 To solve the problem that intelligent devices equipped with deep reinforcement learning agents lack effective security data sharing mechanisms in the intelligent Internet of things, a general federated reinforcement learning (GenFedRL) framework was ...
Biao JIN +4 more
doaj +2 more sources
Journal of Robotics, 2022 Deep reinforcement learning is the technology of artificial neural networks in the field of decision-making and control. The traditional model-free reinforcement learning algorithm requires a large amount of environment interactive data to iterate the ...
Guoqing Ma +3 more
doaj +1 more source
Benchmarking Model-Based Reinforcement Learning
CoRR, 2019 8 main pages, 8 figures; 14 appendix pages, 25 ...
Tingwu Wang +9 more
openaire +2 more sources
MOReL : Model-Based Offline Reinforcement Learning
CoRR, 2020 First two authors contributed equally. Published at NeurIPS 2020. After publication at NeurIPS 2020, (1) D4RL benchmark results have been added; (2) hyper-parameter ablation studies have been added; (3) scope of Lemma 3 has been ...
Rahul Kidambi +3 more
openaire +3 more sources
Computational Psychiatry, 2022 Gambling disorder is a behavioral addiction that negatively impacts personal finances, work, relationships and mental health. In this pre-registered study (https://osf.io/5ptz9/) we investigated the impact of real-life gambling environments on two ...
Ben Wagner, David Mathar, Jan Peters
doaj +1 more source
Model-based Lookahead Reinforcement Learning
CoRR, 2019 Model-based Reinforcement Learning (MBRL) allows data-efficient learning which is required in real world applications such as robotics. However, despite the impressive data-efficiency, MBRL does not achieve the final performance of state-of-the-art Model-free Reinforcement Learning (MFRL) methods. We leverage the strengths of both realms and propose an
Zhang-Wei Hong +2 more
openaire +2 more sources