Data-driven hospitals staff and resources allocation using agent-based simulation and deep reinforcement learning

T Lazebnik - Engineering Applications of Artificial Intelligence, 2023 - Elsevier
Hospital staff and resources allocation (HSRA) is a critical challenge in healthcare systems,
as it involves balancing the demands of patients, the availability of resources, and the need …

Learning useful representations of recurrent neural network weight matrices

V Herrmann, F Faccio, J Schmidhuber - arXiv preprint arXiv:2403.11998, 2024 - arxiv.org
Recurrent Neural Networks (RNNs) are general-purpose parallel-sequential computers. The
program of an RNN is its weight matrix. How to learn useful representations of RNN weights …

Toward complete coverage planning using deep reinforcement learning by trapezoid-based transformable robot

DT Vo, AV Le, TD Ta, M Tran, P Van Duc, MB Vu… - … Applications of Artificial …, 2023 - Elsevier
Shape-shifting robots are the feasible solutions to solve the Complete Coverage Planning
(CCP) problem. These robots can extend the covered areas by reconfiguring their shape to …

Improving deep reinforcement learning by reducing the chain effect of value and policy churn

H Tang, G Berseth - arXiv preprint arXiv:2409.04792, 2024 - arxiv.org
Deep neural networks provide Reinforcement Learning (RL) powerful function
approximators to address large-scale decision-making problems. However, these …

General policy evaluation and improvement by learning to identify few but crucial states

F Faccio, A Ramesh, V Herrmann, J Harb… - arXiv preprint arXiv …, 2022 - arxiv.org
Learning to evaluate and improve policies is a core problem of Reinforcement Learning
(RL). Traditional RL algorithms learn a value function defined for a single policy. A recently …

Representation-driven reinforcement learning

O Nabati, G Tennenholtz… - … Conference on Machine …, 2023 - proceedings.mlr.press
We present a representation-driven framework for reinforcement learning. By representing
policies as estimates of their expected values, we leverage techniques from contextual …

Self-supervised Pretraining for Decision Foundation Model: Formulation, Pipeline and Challenges

X Liu, J Jiao, J Zhang - arXiv preprint arXiv:2401.00031, 2023 - arxiv.org
Decision-making is a dynamic process requiring perception, memory, and reasoning to
make choices and find optimal policies. Traditional approaches to decision-making suffer …

Adaptive Optimization in Evolutionary Reinforcement Learning Using Evolutionary Mutation Rates

Y Zhao, Y Ding, Y Pei - IEEE Access, 2024 - ieeexplore.ieee.org
Deep reinforcement learning (DRL) has achieved notable success in continuous control
tasks. However, it faces challenges that limit its applicability to a wider array of tasks …

Pandr: Fast adaptation to new environments from offline experiences via decoupling policy and environment representations

T Sang, H Tang, Y Ma, J Hao, Y Zheng, Z Meng… - arXiv preprint arXiv …, 2022 - arxiv.org
Deep Reinforcement Learning (DRL) has been a promising solution to many complex
decision-making problems. Nevertheless, the notorious weakness in generalization among …

[PDF][PDF] PoRank: A Practical Framework for Learning to Rank Policies

P Gu, M Zhao, X He, Y Cai, B An - … of the Thirty-Third International Joint …, 2024 - ijcai.org
In many real-world scenarios, we need to select from a set of candidate policies before
online deployment. Although existing off-policy evaluation (OPE) methods can be used to …