Policy gradient and actor-critic learning in continuous time and space: Theory and algorithms
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 …
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 …
affine nonlinear systems. We review four seminal methods that are the centerpieces of the …
Active observing in continuous-time control
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 …
observations in time is a crucial yet unexplored problem, particularly relevant to real-world …
Ode-based recurrent model-free reinforcement learning for pomdps
Neural ordinary differential equations (ODEs) are widely recognized as the standard for
modeling physical mechanisms, which help to perform approximate inference in unknown …
modeling physical mechanisms, which help to perform approximate inference in unknown …
Efficient exploration in continuous-time model-based reinforcement learning
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 …
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 …
We introduce a new model that decomposes independent dynamics of single objects …
Continuous-Time decision transformer for healthcare applications
Offline reinforcement learning (RL) is a promising approach for training intelligent medical
agents to learn treatment policies and assist decision making in many healthcare …
agents to learn treatment policies and assist decision making in many healthcare …
Neural Laplace control for continuous-time delayed systems
Many real-world offline reinforcement learning (RL) problems involve continuous-time
environments with delays. Such environments are characterized by two distinctive features …
environments with delays. Such environments are characterized by two distinctive features …
Neural differential equations for learning to program neural nets through continuous learning rules
Neural ordinary differential equations (ODEs) have attracted much attention as continuous-
time counterparts of deep residual neural networks (NNs), and numerous extensions for …
time counterparts of deep residual neural networks (NNs), and numerous extensions for …
Bellman meets hawkes: Model-based reinforcement learning via temporal point processes
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 …
characterized by the stochastic discrete events and seeks an optimal intervention policy …