papers

Publications (39)

cs.AI2014

Monte Carlo Sampling Methods for Approximating Interactive POMDPs

Prashant Doshi, Piotr J. Gmytrasiewicz

Partially observable Markov decision processes (POMDPs) provide a principled framework for sequential planning in uncertain single agent settings. An extension of POMDPs to multiag…

cs.MA2019

Scalable Decision-Theoretic Planning in Open and Typed Multiagent Systems

Adam Eck, Maulik Shah, Prashant Doshi +1

In open agent systems, the set of agents that are cooperating or competing changes over time and in ways that are nontrivial to predict. For example, if collaborative robots were t…

cs.AI2017

Freeway Merging in Congested Traffic based on Multipolicy Decision Making with Passive Actor Critic

Tomoki Nishi, Prashant Doshi, Danil Prokhorov

Freeway merging in congested traffic is a significant challenge toward fully automated driving. Merging vehicles need to decide not only how to merge into a spot, but also where to…

cs.LG2020

Cooperative-Competitive Reinforcement Learning with History-Dependent Rewards

Keyang He, Bikramjit Banerjee, Prashant Doshi

Consider a typical organization whose worker agents seek to collectively cooperate for its general betterment. However, each individual agent simultaneously seeks to act to secure…

cs.LG2018

Reinforcement Learning for Heterogeneous Teams with PALO Bounds

Roi Ceren, Prashant Doshi, Keyang He

We introduce reinforcement learning for heterogeneous teams in which rewards for an agent are additively factored into local costs, stimuli unique to each agent, and global rewards…

cs.RO2020

SA-Net: Deep Neural Network for Robot Trajectory Recognition from RGB-D Streams

Nihal Soans, Ehsan Asali, Yi Hong +1

Learning from demonstration (LfD) and imitation learning offer new paradigms for transferring task behavior to robots. A class of methods that enable such online learning require t…

cs.LG2021

Many Agent Reinforcement Learning Under Partial Observability

Keyang He, Prashant Doshi, Bikramjit Banerjee

Recent renewed interest in multi-agent reinforcement learning (MARL) has generated an impressive array of techniques that leverage deep reinforcement learning, primarily actor-crit…

cs.MA2022

SIPOMDPLite-Net: Lightweight, Self-Interested Learning and Planning in POSGs with Sparse Interactions

Gengyu Zhang, Prashant Doshi

This work introduces sIPOMDPLite-net, a deep neural network (DNN) architecture for decentralized, self-interested agent control in partially observable stochastic games (POSGs) wit…

cs.LG2024

IRL for Restless Multi-Armed Bandits with Applications in Maternal and Child Health

Gauri Jain, Pradeep Varakantham, Haifeng Xu +3

Public health practitioners often have the goal of monitoring patients and maximizing patients' time spent in "favorable" or healthy states while being constrained to using limited…

cs.LG2016

Dynamic Sum Product Networks for Tractable Inference on Sequence Data (Extended Version)

Mazen Melibari, Pascal Poupart, Prashant Doshi +1

Sum-Product Networks (SPN) have recently emerged as a new class of tractable probabilistic graphical models. Unlike Bayesian networks and Markov networks where inference may be exp…

cs.LG2018

A Framework and Method for Online Inverse Reinforcement Learning

Saurabh Arora, Prashant Doshi, Bikramjit Banerjee

Inverse reinforcement learning (IRL) is the problem of learning the preferences of an agent from the observations of its behavior on a task. While this problem has been well invest…

cs.CR2020

GrAALF:Supporting Graphical Analysis of Audit Logs for Forensics

Omid Setayeshfar, Christian Adkins, Matthew Jones +2

System-level audit logs often play a critical role in computer forensics. They capture low-level interactions between programs and users in much detail, making them a rich source o…

cs.RO2024

Visual IRL for Human-Like Robotic Manipulation

Ehsan Asali, Prashant Doshi

We present a novel method for collaborative robots (cobots) to learn manipulation tasks and perform them in a human-like manner. Our method falls under the learn-from-observation (…

cs.LG2026

Inversely Learning Transferable Rewards via Abstracted States

Yikang Gui, Prashant Doshi

Inverse reinforcement learning (IRL) has progressed significantly toward accurately learning the underlying rewards in both discrete and continuous domains from behavior data. The…

cs.LG2020

Maximum Entropy Multi-Task Inverse RL

Saurabh Arora, Bikramjit Banerjee, Prashant Doshi

Multi-task IRL allows for the possibility that the expert could be switching between multiple ways of solving the same problem, or interleaving demonstrations of multiple tasks. Th…

cs.RO2025

FRESHR-GSI: A Generalized Safety Model and Evaluation Framework for Mobile Robots in Multi-Human Environments

Pranav Pandey, Ramviyas Parasuraman, Prashant Doshi

Human safety is critical in applications involving close human-robot interactions (HRI) and is a key aspect of physical compatibility between humans and robots. While measures of h…

cs.LG2023

A Novel Variational Lower Bound for Inverse Reinforcement Learning

Yikang Gui, Prashant Doshi

Inverse reinforcement learning (IRL) seeks to learn the reward function from expert trajectories, to understand the task for imitation or collaboration thereby removing the need fo…

cs.RO2021

Marginal MAP Estimation for Inverse RL under Occlusion with Observer Noise

Prasanth Sengadu Suresh, Prashant Doshi

We consider the problem of learning the behavioral preferences of an expert engaged in a task from noisy and partially-observable demonstrations. This is motivated by real-world ap…

cs.MA2020

Active Deception using Factored Interactive POMDPs to Recognize Cyber Attacker's Intent

Aditya Shinde, Prashant Doshi, Omid Setayeshfar

This paper presents an intelligent and adaptive agent that employs deception to recognize a cyber adversary's intent. Unlike previous approaches to cyber deception, which mainly fo…

cs.MA2015

Individual Planning in Agent Populations: Exploiting Anonymity and Frame-Action Hypergraphs

Ekhlas Sonu, Yingke Chen, Prashant Doshi

Interactive partially observable Markov decision processes (I-POMDP) provide a formal framework for planning for a self-interested agent in multiagent settings. An agent operating…

cs.MA2014

Team Behavior in Interactive Dynamic Influence Diagrams with Applications to Ad Hoc Teams

Muthukumaran Chandrasekaran, Prashant Doshi, Yifeng Zeng +1

Planning for ad hoc teamwork is challenging because it involves agents collaborating without any prior coordination or communication. The focus is on principled methods for a singl…

cs.AI2020

Recurrent Sum-Product-Max Networks for Decision Making in Perfectly-Observed Environments

Hari Teja Tatavarti, Prashant Doshi, Layton Hayes

Recent investigations into sum-product-max networks (SPMN) that generalize sum-product networks (SPN) offer a data-driven alternative for decision making, which has predominantly r…

cs.AI2026

PLATO: Pointer Learner for Agent and Task Openness

Alireza Saleh Abadi, Leen-Kiat Soh, Daniel Alan Redder +2

Open agent systems (OASYS) are increasingly prevalent in real-world domains where the sets of agents and tasks change unpredictably over time. Such openness, including agent openne…

cs.LG2023

Latent Interactive A2C for Improved RL in Open Many-Agent Systems

Keyang He, Prashant Doshi, Bikramjit Banerjee

There is a prevalence of multiagent reinforcement learning (MARL) methods that engage in centralized training. But, these methods involve obtaining various types of information fro…

cs.LG2022

IRL with Partial Observations using the Principle of Uncertain Maximum Entropy

Kenneth Bogert, Yikang Gui, Prashant Doshi

The principle of maximum entropy is a broadly applicable technique for computing a distribution with the least amount of information possible while constrained to match empirically…

cs.LG2026

ConTraIRL: Factorized Contrastive Abstractions for Transferable IRL

Yikang Gui, Bikramjit Banerjee, Prashant Doshi

Reward transfer in Inverse Reinforcement Learning (IRL) is unreliable when policies must generalize to unseen combinations of environment dynamics and task goals. We propose Factor…

cs.RO2025

Integrating Perceptions: A Human-Centered Physical Safety Model for Human-Robot Interaction

Pranav Pandey, Ramviyas Parasuraman, Prashant Doshi

Ensuring safety in human-robot interaction (HRI) is essential to foster user trust and enable the broader adoption of robotic systems. Traditional safety models primarily rely on s…

cs.MA2025

Inaugural MOASEI Competition at AAMAS'2025: A Technical Report

Ceferino Patino, Tyler J. Billings, Alireza Saleh Abadi +4

We present the Methods for Open Agent Systems Evaluation Initiative (MOASEI) Competition, a multi-agent AI benchmarking event designed to evaluate decision-making under open-world…

cs.RO2024

Analyzing Human Perceptions of a MEDEVAC Robot in a Simulated Evacuation Scenario

Tyson Jordan, Pranav Pandey, Prashant Doshi +2

The use of autonomous systems in medical evacuation (MEDEVAC) scenarios is promising, but existing implementations overlook key insights from human-robot interaction (HRI) research…

cs.CR2025

Modeling Behavioral Preferences of Cyber Adversaries Using Inverse Reinforcement Learning

Aditya Shinde, Prashant Doshi

This paper presents a holistic approach to attacker preference modeling from system-level audit logs using inverse reinforcement learning (IRL). Adversary modeling is an important…

cs.CV2024

MVSA-Net: Multi-View State-Action Recognition for Robust and Deployable Trajectory Generation

Ehsan Asali, Prashant Doshi, Jin Sun

The learn-from-observation (LfO) paradigm is a human-inspired mode for a robot to learn to perform a task simply by watching it being performed. LfO can facilitate robot integratio…

cs.RO2017

Inverse Reinforcement Learning Under Noisy Observations

Shervin Shahryari, Prashant Doshi

We consider the problem of performing inverse reinforcement learning when the trajectory of the expert is not perfectly observed by the learner. Instead, a noisy continuous-time ob…

cs.IR2012

From Questions to Effective Answers: On the Utility of Knowledge-Driven Querying Systems for Life Sciences Data

Amir H. Asiaee, Prashant Doshi, Todd Minning +4

We compare two distinct approaches for querying data in the context of the life sciences. The first approach utilizes conventional databases to store the data and intuitive form-ba…

cs.AI2014

Exploiting Model Equivalences for Solving Interactive Dynamic Influence Diagrams

Yifeng Zeng, Prashant Doshi

We focus on the problem of sequential decision making in partially observable environments shared with other agents of uncertain types having similar or conflicting objectives. Thi…

cs.RO2024

Open Human-Robot Collaboration using Decentralized Inverse Reinforcement Learning

Prasanth Sengadu Suresh, Siddarth Jain, Prashant Doshi +1

The growing interest in human-robot collaboration (HRC), where humans and robots cooperate towards shared goals, has seen significant advancements over the past decade. While previ…

cs.LG2021

A Hierarchical Bayesian model for Inverse RL in Partially-Controlled Environments

Kenneth Bogert, Prashant Doshi

Robots learning from observations in the real world using inverse reinforcement learning (IRL) may encounter objects or agents in the environment, other than the expert, that cause…

cs.AI2017

Actor-Critic for Linearly-Solvable Continuous MDP with Partially Known Dynamics

Tomoki Nishi, Prashant Doshi, Michael R. James +1

In many robotic applications, some aspects of the system dynamics can be modeled accurately while others are difficult to obtain or model. We present a novel reinforcement learning…

cs.LG2020

A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress

Saurabh Arora, Prashant Doshi

Inverse reinforcement learning (IRL) is the problem of inferring the reward function of an agent, given its policy or observed behavior. Analogous to RL, IRL is perceived both as a…

cs.MA2026

Second MOASEI Competition at AAMAS'2026: A Technical Report

Ceferino Patino, Tyler J. Billings, Alireza Saleh Abadi +4

We describe the 2026 Methods for Open Agent Systems Evaluation Initiative (MOASEI) Competition, a benchmark event for evaluating multi-agent decision-making under open-system condi…