Maximum entropy RL (provably) solves some robust RL problems
B Eysenbach, S Levine - arXiv preprint arXiv:2103.06257, 2021 - arxiv.org
Many potential applications of reinforcement learning (RL) require guarantees that the agent
will perform well in the face of disturbances to the dynamics or reward function. In this paper …
will perform well in the face of disturbances to the dynamics or reward function. In this paper …
DRLinFluids: An open-source Python platform of coupling deep reinforcement learning and OpenFOAM
We propose an open-source Python platform for applications of deep reinforcement learning
(DRL) in fluid mechanics. DRL has been widely used in optimizing decision making in …
(DRL) in fluid mechanics. DRL has been widely used in optimizing decision making in …
[HTML][HTML] Deep reinforcement learning for computational fluid dynamics on HPC systems
M Kurz, P Offenhäuser, D Viola, O Shcherbakov… - Journal of …, 2022 - Elsevier
Reinforcement learning (RL) is highly suitable for devising control strategies in the context of
dynamical systems. A prominent instance of such a dynamical system is the system of …
dynamical systems. A prominent instance of such a dynamical system is the system of …
If MaxEnt RL is the answer, what is the question?
B Eysenbach, S Levine - arXiv preprint arXiv:1910.01913, 2019 - arxiv.org
Experimentally, it has been observed that humans and animals often make decisions that do
not maximize their expected utility, but rather choose outcomes randomly, with probability …
not maximize their expected utility, but rather choose outcomes randomly, with probability …
[HTML][HTML] Relexi—A scalable open source reinforcement learning framework for high-performance computing
Relexi is an open source reinforcement learning (RL) framework written in Python and
based on TensorFlow's RL library TF-Agents. Relexi allows to employ RL for environments …
based on TensorFlow's RL library TF-Agents. Relexi allows to employ RL for environments …
[HTML][HTML] Evaluation of blood glucose level control in type 1 diabetic patients using deep reinforcement learning
Diabetes mellitus is a disease associated with abnormally high levels of blood glucose due
to a lack of insulin. Combining an insulin pump and continuous glucose monitor with a …
to a lack of insulin. Combining an insulin pump and continuous glucose monitor with a …
Learning assembly tasks in a few minutes by combining impedance control and residual recurrent reinforcement learning
Adapting to uncertainties is essential yet challenging for robots while conducting assembly
tasks in real‐world scenarios. Reinforcement learning (RL) methods provide a promising …
tasks in real‐world scenarios. Reinforcement learning (RL) methods provide a promising …
[HTML][HTML] DRLFluent: A distributed co-simulation framework coupling deep reinforcement learning with Ansys-Fluent on high-performance computing systems
For active flow control (AFC), several frameworks have been developed to enable dynamic
interactions between deep reinforcement learning (DRL) agents and computational fluids …
interactions between deep reinforcement learning (DRL) agents and computational fluids …
Variational empowerment as representation learning for goal-based reinforcement learning
Learning to reach goal states and learning diverse skills through mutual information (MI)
maximization have been proposed as principled frameworks for self-supervised …
maximization have been proposed as principled frameworks for self-supervised …
[HTML][HTML] Reliability evaluation of reinforcement learning methods for mechanical systems with increasing complexity
P Manzl, O Rogov, J Gerstmayr, A Mikkola… - Multibody System …, 2023 - Springer
Reinforcement learning (RL) is one of the emerging fields of artificial intelligence (AI)
intended for designing agents that take actions in the physical environment. RL has many …
intended for designing agents that take actions in the physical environment. RL has many …