3 citations · 5 across the 9 of their papers we have counts for
10 papers
Explainably Safe Reinforcement Learning
Sabine Rieder, Stefan Pranger, Debraj Chakraborty +2
Trust in a decision-making system requires both safety guarantees and the ability to interpret and understand its behavior. This is particularly important for learned systems, whos…
Synthesizing POMDP Policies: Sampling Meets Model-checking via Learning
Debraj Chakraborty, Anirban Majumdar, Prince Mathew +2
Partially Observable Markov Decision Processes (POMDPs) are the standard framework for decision-making under uncertainty. While sampling-based methods scale well, they lack formal…
Resilient Strategies for Stochastic Systems: How Much Does It Take to Break a Winning Strategy?
Kush Grover, Markel Zubia, Debraj Chakraborty +3
We study the problem of resilient strategies in the presence of uncertainty. Resilient strategies enable an agent to make decisions that are robust against disturbances. In particu…
Planar Herding of Multiple Evaders with a Single Herder
Rishabh Kumar Singh, Debraj Chakraborty
A planar herding problem is considered, where a superior pursuer herds a flock of non-cooperative, inferior evaders around a predefined target point. An inverse square law of repul…
Explaining Control Policies through Predicate Decision Diagrams
Debraj Chakraborty, Clemens Dubslaff, Sudeep Kanav +2
Safety-critical controllers of complex systems are hard to construct manually. Automated approaches such as controller synthesis or learning provide a tempting alternative but usua…
Explainable Representation of Finite-Memory Policies for POMDPs using Decision Trees
Muqsit Azeem, Debraj Chakraborty, Sudeep Kanav +1
Partially Observable Markov Decision Processes (POMDPs) are a fundamental framework for decision-making under uncertainty and partial observability. Since in general optimal polici…
1-2-3-Go! Policy Synthesis for Parameterized Markov Decision Processes via Decision-Tree Learning and Generalization
Muqsit Azeem, Debraj Chakraborty, Sudeep Kanav +4
Despite the advances in probabilistic model checking, the scalability of the verification methods remains limited. In particular, the state space often becomes extremely large when…
Learning Explainable and Better Performing Representations of POMDP Strategies
Alexander Bork, Debraj Chakraborty, Kush Grover +2
Strategies for partially observable Markov decision processes (POMDP) typically require memory. One way to represent this memory is via automata. We present a method to learn an au…
Learning from similar systems and online data-driven LQR using iterative randomised data compression
Vatsal Kedia, Sneha Susan George, Debraj Chakraborty
The problem of data-driven recursive computation of receding horizon LQR control through a randomized combination of online/current and historical/recorded data is considered. It i…
Safe Learning for Near Optimal Scheduling
Damien Busatto-Gaston, Debraj Chakraborty, Shibashis Guha +2
In this paper, we investigate the combination of synthesis, model-based learning, and online sampling techniques to obtain safe and near-optimal schedulers for a preemptible task s…