arXiv subjects

Shashi Shekhar Jha

Publications and source records attributed to Shashi Shekhar Jha.

5 recordsLinked to original sources

arXiv2026

PLACO: A Multi-Stage Framework for Cost-Effective Performance in Human-AI Teams

Human-AI teams play a pivotal role in improving overall system performance when neither the human nor the model can achieve such performance on their own. With the advent of powerful and accessible Generative AI models, several mundane tasks have morphed into Human-AI team tasks. From writing essays to developing advanced algorithms, humans have found that using AI assistance has led to an accelerated work pace like never before. In classification tasks, where the final output is a single hard label, it is crucial to address the combination of human and model output. Prior work elegantly solves this problem using Bayes rule, using the assumption that human and model output are conditionally independent given the ground truth. Specifically, it discusses a combination method to combine a single deterministic labeler (the human) and a probabilistic labeler (the classifier model) using the model's instance-level and the human's class-level calibrated probabilities.

cs.AI↗

arXiv2026

CAPSULE: Control-Theoretic Action Perturbations for Safe Uncertainty-Aware Reinforcement Learning

Ensuring safe exploration in high-dimensional systems with unknown dynamics remains a significant challenge. Existing safe reinforcement learning methods often provide safety guarantees only in expectation, which can still lead to safety violations. Control-theoretic approaches, in contrast, offer hard constraint-based safety guarantees but typically assume access to known system dynamics or require accurate estimation of control-affine models. In this paper, we propose a safe reinforcement learning framework that learns a probabilistic control-affine dynamics model in an offline setting. The learned model is leveraged to explicitly construct control barrier functions (CBFs) that incorporate model uncertainty to provide conservative safety constraints. These CBF constraints are enforced through an online constraint-based action correction mechanism, enabling safe exploration without overly restricting task performance. Empirical evaluations on nonlinear, complex continuous-control benchmarks demonstrate that our approach achieves returns comparable to those of existing baselines while significantly reducing safety violations.

cs.LG↗

arXiv2025

DQ4FairIM: Fairness-aware Influence Maximization using Deep Reinforcement Learning

The Influence Maximization (IM) problem aims to select a set of seed nodes within a given budget to maximize the spread of influence in a social network. However, real-world social networks have several structural inequalities, such as dominant majority groups and underrepresented minority groups. If these inequalities are not considered while designing IM algorithms, the outcomes might be biased, disproportionately benefiting majority groups while marginalizing minorities. In this work, we address this gap by designing a fairness-aware IM method using Reinforcement Learning (RL) that ensures equitable influence outreach across all communities, regardless of protected attributes. Fairness is incorporated using a maximin fairness objective, which prioritizes improving the outreach of the least-influenced group, pushing the solution toward an equitable influence distribution. We propose a novel fairness-aware deep RL method, called DQ4FairIM, that maximizes the expected number of influenced nodes by learning an RL policy. The learnt policy ensures that minority groups formulate the IM problem as a Markov Decision Process (MDP) and use deep Q-learning, combined with the Structure2Vec network embedding, earning together with Structure2Vec network embedding to solve the MDP. We perform extensive experiments on synthetic benchmarks and real-world networks to compare our method with fairness-agnostic and fairness-aware baselines. The results show that our method achieves a higher level of fairness while maintaining a better fairness-performance trade-off than baselines. Additionally, our approach learns effective seeding policies that generalize across problem instances without retraining, such as varying the network size or the number of seed nodes.

cs.LG↗

arXiv2023

Chasing the Intruder: A Reinforcement Learning Approach for Tracking Intruder Drones

Drones are becoming versatile in a myriad of applications. This has led to the use of drones for spying and intruding into the restricted or private air spaces. Such foul use of drone technology is dangerous for the safety and security of many critical infrastructures. In addition, due to the varied low-cost design and agility of the drones, it is a challenging task to identify and track them using the conventional radar systems. In this paper, we propose a reinforcement learning based approach for identifying and tracking any intruder drone using a chaser drone. Our proposed solution uses computer vision techniques interleaved with the policy learning framework of reinforcement learning to learn a control policy for chasing the intruder drone. The whole system has been implemented using ROS and Gazebo along with the Ardupilot based flight controller. The results show that the reinforcement learning based policy converges to identify and track the intruder drone. Further, the learnt policy is robust with respect to the change in speed or orientation of the intruder drone.

cs.RO↗

arXiv2018

On Ordering Multi-Robot Task Executions within a Cyber Physical System

With robots entering the world of Cyber Physical Systems (CPS), ordering the execution of allocated tasks during run-time becomes crucial. This is so because, in a real world, there can be several physical tasks that use shared resources that need to be executed concurrently. In this paper, we propose a mechanism to solve this issue of ordering task executions within a CPS which inherently handles mutual exclusion. The mechanism caters to a decentralized and distributed CPS comprising nodes such as computers, robots and sensor nodes, and uses mobile software agents that knit through them to aid the execution of the various tasks while also ensuring mutual exclusion of shared resources. The computations, communications and control, are achieved through these mobile agents. Physical execution of the tasks is performed by the robots in an asynchronous and pipelined manner without the use of a clock. The mechanism also features addition and deletion of tasks and insertion and removal of robots facilitating \textit{On-The-Fly Programming}. As an application, a Warehouse Management System as a CPS has been implemented. The paper concludes with the results and discussions on using the mechanism in both emulated and real world environments.

cs.DC↗