Soutrik Bandyopadhyay- PhD
- PhD Student at Indian Institute of Technology Delhi
Soutrik Bandyopadhyay
- PhD
- PhD Student at Indian Institute of Technology Delhi
About
7
Publications
813
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
17
Citations
Introduction
I am currently working on the safety-first application of Reinforcement Learning algorithms in the context of Control of Dynamical Systems.
Current institution
Education
July 2015 - July 2020
Publications
Publications (7)
We introduce behavioral inequalities as a way to model dynamical systems defined by inequalities among their variables of interest. We claim that such a formulation enables the representation of safety-aware dynamical systems, systems with bounds on disturbances, practical design limits and operational boundaries, etc. We develop a necessary and su...
This paper proposes a safe reinforcement learning(RL) algorithm that solves the constrained optimal control problem for continuous-time nonlinear systems with uncertain dynamics. We formulate the safe RL problem as minimizing a Lagrangian involving the cost functional and a user-defined barrier Lyapunov function(BLF) encoding the state constraints....
Q-learning is a promising method for solving optimal control problems for uncertain systems without the explicit need for system identification. However, approaches for continuous-time Q-learning have limited provable safety guarantees, which restrict their applicability to real-time safety-critical systems. This paper proposes a safe Q-learning al...
This paper proposes an on-policy reinforcement learning (RL) control algorithm that solves the optimal regulation problem for a class of uncertain continuous-time nonlinear systems under user-defined state constraints. We formulate the safe RL problem as the minimization of the Hamiltonian subject to a constraint on the time-derivative of a barrier...
Continuum robots have been very popular in the recent days due to their wide spread applications in space, defence, medical, underwater, industries etc. Modelling of these types of robots is difficult due to their highly nonlinear dynamic characteristic which necessitates the need for model-less intelligent control. In this paper two intelligent mo...
