53 citations · 232 across the 44 of their papers we have counts for
8 papers · 1 filter
Predicting Citi Bike Demand Evolution Using Dynamic Graphs
Alexander Saff, Mayur Bhandary, Siddharth Srivastava
Bike sharing systems often suffer from poor capacity management as a result of variable demand. These bike sharing systems would benefit from models to predict demand in order to m…
Hierarchical Decomposition and Analysis for Generalized Planning
Siddharth Srivastava
This paper presents new methods for analyzing and evaluating generalized plans that can solve broad classes of related planning problems. Although synthesis and learning of general…
Learning Dynamic Abstract Representations for Sample-Efficient Reinforcement Learning
Mehdi Dadvar, Rashmeet Kaur Nayyar, Siddharth Srivastava
In many real-world problems, the learning agent needs to learn a problem's abstractions and solution simultaneously. However, most such abstractions need to be designed and refined…
Multi-Task Option Learning and Discovery for Stochastic Path Planning
Naman Shah, Siddharth Srivastava
This paper addresses the problem of reliably and efficiently solving broad classes of long-horizon stochastic path planning problems. Starting with a vanilla RL formulation with a…
Relational Abstractions for Generalized Reinforcement Learning on Symbolic Problems
Rushang Karia, Siddharth Srivastava
Reinforcement learning in problems with symbolic state spaces is challenging due to the need for reasoning over long horizons. This paper presents a new approach that utilizes rela…
Learning Generalized Policy Automata for Relational Stochastic Shortest Path Problems
Rushang Karia, Rashmeet Kaur Nayyar, Siddharth Srivastava
Several goal-oriented problems in the real-world can be naturally expressed as Stochastic Shortest Path Problems (SSPs). However, the computational complexity of solving SSPs makes…
Differential Assessment of Black-Box AI Agents
Rashmeet Kaur Nayyar, Pulkit Verma, Siddharth Srivastava
Much of the research on learning symbolic models of AI agents focuses on agents with stationary models. This assumption fails to hold in settings where the agent's capabilities may…
Using Deep Learning to Bootstrap Abstractions for Hierarchical Robot Planning
Naman Shah, Siddharth Srivastava
This paper addresses the problem of learning abstractions that boost robot planning performance while providing strong guarantees of reliability. Although state-of-the-art hierarch…