msramada

Active-Learning-Reinforcement-Learning

This code can be used to reproduce the results in our paper ``Actively Learning Reinforcement Learning: A Stochastic Optimal Control Approach''.

Control-Importance-Distribution-Algorithm-CIDA-

This code can be used to reproduce the results in our paper ``A Control Approach for Nonlinear Stochastic State Uncertain Systems with Probabilistic Safety Guarantees''.

data-conforming-control

This code can be used to reproduce the results in our paper ``Data-conforming data-driven control: avoiding premature generalizations beyond data''

DataEnabledControl.jl

This is the Julia implementation of the behavioral control DeePC algorithm.

Efficient-Particle-Filter-OOP

A particle filter as a class and its particles and their likelihoods are attributes. The measurement- and time-update steps are listed as methods.

Extended-Kalman-Filter-UsingPyTorchAutoGrad

Uses PyTorch tensors and autograd | The extended Kalman filtering algorithm as a class: mean and covariance are attributes and propagation in time are methods | PyTorch autograd is used to return the jacobians of the state and measurement dynamics | Example.py presents a quick demo.

floodGatesUp-DeePC

This code can be used to reproduce the results in our paper ``Floodgates up to contain the DeePC and limit extrapolation''.

linearizing-uncertainty-for-control

This code can be used to reproduce the results in our paper ``Extended Kalman filter---Koopman operator for tractable stochastic optimal control'.

Policy-Iteration-Markov-Decision-Process-OOP

Policy iteration algorithm applied on finite state and action spaces Markov decision process.

State-Selection-Algorithm

The Python codes, of the algorithms for linear and nonlinear systems, used in our paper``State estimation for control: an approach for output-feedback stochastic MPC''.

msramada/linearizing-uncertainty-for-control

This code can be used to reproduce the results in our paper ``Extended Kalman filter---Koopman operator for tractable stochastic optimal control'.

msramada/Active-Learning-Reinforcement-Learning

This code can be used to reproduce the results in our paper ``Actively Learning Reinforcement Learning: A Stochastic Optimal Control Approach''.

msramada/DataEnabledControl.jl

This is the Julia implementation of the behavioral control DeePC algorithm.

msramada/Extended-Kalman-Filter-UsingPyTorchAutoGrad

Uses PyTorch tensors and autograd | The extended Kalman filtering algorithm as a class: mean and covariance are attributes and propagation in time are methods | PyTorch autograd is used to return the jacobians of the state and measurement dynamics | Example.py presents a quick demo.

msramada/State-Selection-Algorithm

The Python codes, of the algorithms for linear and nonlinear systems, used in our paper``State estimation for control: an approach for output-feedback stochastic MPC''.

msramada/Control-Importance-Distribution-Algorithm-CIDA-

This code can be used to reproduce the results in our paper ``A Control Approach for Nonlinear Stochastic State Uncertain Systems with Probabilistic Safety Guarantees''.

msramada/Efficient-Particle-Filter-OOP

A particle filter as a class and its particles and their likelihoods are attributes. The measurement- and time-update steps are listed as methods.

msramada/FixedPointEM_Algorithm

This code can be used to reproduce the results in our paper ``Maximum Likelihood recursive state estimation using the Expectation Maximization algorithm''.

msramada/MonteCarlo_DynamicProgramming

Monte Carlo Grid Dynamic Programming: Almost Sure Convergence and Probability Constraints

msramada/Near-Expert-WarmUp-Reinforcement-Learning

Reinforcement learning algorithm initialized by supervised learning of a nearly expert agent.

msramada/Reinforcement-learning-with-active-learning-PyTorch

Using ideas from stochastic optimal control in reinforcement learning.

msramada/data-conforming-control

This code can be used to reproduce the results in our paper ``Data-conforming data-driven control: avoiding premature generalizations beyond data''

msramada/Policy-Iteration-Markov-Decision-Process-OOP

Policy iteration algorithm applied on finite state and action spaces Markov decision process.

msramada/msramada

msramada/msramada.github.io

msramada/On-the-unit-commitment-problems