Policy gradient and actor-critic learning in continuous time and space: Theory and algorithms

Y Jia, XY Zhou - Journal of Machine Learning Research, 2022 - jmlr.org
We study policy gradient (PG) for reinforcement learning in continuous time and space
under the regularized exploratory formulation developed by Wang et al.(2020). We …

Continuous-time reinforcement learning control: A review of theoretical results, insights on performance, and needs for new designs

BA Wallace, J Si - IEEE Transactions on Neural Networks and …, 2023 - ieeexplore.ieee.org
This exposition discusses continuous-time reinforcement learning (CT-RL) for the control of
affine nonlinear systems. We review four seminal methods that are the centerpieces of the …

Active observing in continuous-time control

S Holt, A Hüyük… - Advances in Neural …, 2024 - proceedings.neurips.cc
The control of continuous-time environments while actively deciding when to take costly
observations in time is a crucial yet unexplored problem, particularly relevant to real-world …

Ode-based recurrent model-free reinforcement learning for pomdps

X Zhao, D Zhang, H Liyuan… - Advances in Neural …, 2023 - proceedings.neurips.cc
Neural ordinary differential equations (ODEs) are widely recognized as the standard for
modeling physical mechanisms, which help to perform approximate inference in unknown …

Efficient exploration in continuous-time model-based reinforcement learning

L Treven, J Hübotter, F Dorfler… - Advances in Neural …, 2024 - proceedings.neurips.cc
Reinforcement learning algorithms typically consider discrete-time dynamics, even though
the underlying systems are often continuous in time. In this paper, we introduce a model …

Learning interacting dynamical systems with latent gaussian process odes

Ç Yıldız, M Kandemir… - Advances in Neural …, 2022 - proceedings.neurips.cc
We study uncertainty-aware modeling of continuous-time dynamics of interacting objects.
We introduce a new model that decomposes independent dynamics of single objects …

Continuous-Time decision transformer for healthcare applications

Z Zhang, H Mei, Y Xu - International Conference on Artificial …, 2023 - proceedings.mlr.press
Offline reinforcement learning (RL) is a promising approach for training intelligent medical
agents to learn treatment policies and assist decision making in many healthcare …

Neural Laplace control for continuous-time delayed systems

S Holt, A Hüyük, Z Qian, H Sun… - International …, 2023 - proceedings.mlr.press
Many real-world offline reinforcement learning (RL) problems involve continuous-time
environments with delays. Such environments are characterized by two distinctive features …

Neural differential equations for learning to program neural nets through continuous learning rules

K Irie, F Faccio, J Schmidhuber - Advances in Neural …, 2022 - proceedings.neurips.cc
Neural ordinary differential equations (ODEs) have attracted much attention as continuous-
time counterparts of deep residual neural networks (NNs), and numerous extensions for …

Bellman meets hawkes: Model-based reinforcement learning via temporal point processes

C Qu, X Tan, S Xue, X Shi, J Zhang… - Proceedings of the AAAI …, 2023 - ojs.aaai.org
We consider a sequential decision making problem where the agent faces the environment
characterized by the stochastic discrete events and seeks an optimal intervention policy …