Ejemplos de diversas fuentes. Examples from various sources. Related to GNU Octave

Alternative (torch) author implementation of algorithms from the NeurIPS 2024 paper "Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning"

End-to-end Python implementation of Huang's (2025) continuous-time RL methodology for asset-liability management. Features model-free soft actor-critic with adaptive exploration, entropy regularization, and Euler-Maruyama SDE simulation. Includes 7 baselines (SAC/PPO/DDPG/CPPI/ACS/MBP), parallelized execution, and Wilcoxon statistical validation.

A continuous depth language model framework in Julia, implementing Neural ODE Transformers, custom continuous attention integrators, reversible depth architectures, adjoint-based training, and efficient KV-cached inference.

A Continuous-time Markov Chain is a type of Markov Chain where the time between transitions is modeled by a probability distribution, rather than being fixed.

🤖 Leverage continuous-time reinforcement learning to optimize asset-liability management and enhance financial decision-making.

An Adaptive Tightly-coupled Motion Estimator for Multi-LiDAR, Multi-Camera, and Multi-IMU Systems via Continuous-time Optimization

Exploring relationships between discrete and continuous time models

Research compendium for the manuscript Pesigan, I. J. A., Russell, M. A., & Chow, S.-M. (2025). Inferences and Effect Sizes for Direct, Indirect, and Total Effects in Continuous-Time Mediation Models. Psychological Methods.

Code for the paper Multilevel Particle Filters for the Non-Linear Filtering Problem in Continuous Time

cTMed: Continuous-Time Mediation (Pesigan, Russell, & Chow, 2025: https://doi.org/10.1037/met0000779).

A framework for hierarchical modelling, simulation and analysis of dynamic systems

A Julia package that provides high-level abstractions for simulating and deploying stochastic filters

Author implementation of DSUP(q) algorithms from the NeurIPS 2024 paper "Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning"

Parametric analysis/visualization of model/measurement/simulation results

Simplest simulation to use non-Exponential transitions

Collection of discrete- and continuous-time motion parametrizations.

Neural Laplace Control for Continuous-time Delayed Systems - an offline RL method combining Neural Laplace dynamics model and MPC planner to achieve near-expert policy performance in environments with irregular time intervals and an unknown constant delay.

Official repository of SFUISE, a novel continuous-time UWB-inertial state estimation framework based on sliding-window spline fusion.

PyTorch implementation of the NCDSSM models presented in the ICML '23 paper "Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series".