Search Results for author: Subbarao Kambhampati

Found 93 papers, 11 papers with code

Algorithmic Language Models with Neurally Compiled Libraries

no code implementations6 Jul 2024 Lucas Saldyt, Subbarao Kambhampati

Important tasks such as reasoning and planning are fundamentally algorithmic, meaning that solving them robustly requires acquiring true reasoning or planning algorithms, rather than shortcuts.

Robust Planning with LLM-Modulo Framework: Case Study in Travel Planning

no code implementations31 May 2024 Atharva Gundawar, Mudit Verma, Lin Guan, Karthik Valmeekam, Siddhant Bhambri, Subbarao Kambhampati

As the applicability of Large Language Models (LLMs) extends beyond traditional text processing tasks, there is a burgeoning interest in their potential to excel in planning and reasoning assignments, realms traditionally reserved for System 2 cognitive competencies.

Efficient Reinforcement Learning via Large Language Model-based Search

no code implementations24 May 2024 Siddhant Bhambri, Amrita Bhattacharjee, Huan Liu, Subbarao Kambhampati

Given, that Large Language Models (LLMs) have rapidly gained prominence across a magnitude of natural language tasks, we aim to answer the following question: Can we leverage LLMs to construct a reward shaping function that can boost the sample efficiency of an RL agent?

Language Modelling Large Language Model +2

On the Brittle Foundations of ReAct Prompting for Agentic Large Language Models

no code implementations22 May 2024 Mudit Verma, Siddhant Bhambri, Subbarao Kambhampati

In this paper we examine these claims of ReAct based prompting in improving agentic LLMs for sequential decision-making.

Decision Making

Chain of Thoughtlessness? An Analysis of CoT in Planning

no code implementations8 May 2024 Kaya Stechly, Karthik Valmeekam, Subbarao Kambhampati

Large language model (LLM) performance on reasoning problems typically does not generalize out of distribution.

Language Modelling Large Language Model

Can Large Language Models Reason and Plan?

no code implementations7 Mar 2024 Subbarao Kambhampati

While humans sometimes do show the capability of correcting their own erroneous guesses with self-critiquing, there seems to be no basis for that assumption in the case of LLMs.

On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks

no code implementations12 Feb 2024 Kaya Stechly, Karthik Valmeekam, Subbarao Kambhampati

While the initial optimism that reasoning might emerge automatically with scale has been tempered thanks to a slew of counterexamples--ranging from multiplication to simple planning--there persists a wide spread belief that LLMs can self-critique and improve their own solutions in an iterative fashion.

"Task Success" is not Enough: Investigating the Use of Video-Language Models as Behavior Critics for Catching Undesirable Agent Behaviors

no code implementations6 Feb 2024 Lin Guan, Yifan Zhou, Denis Liu, Yantian Zha, Heni Ben Amor, Subbarao Kambhampati

Large-scale generative models are shown to be useful for sampling meaningful candidate solutions, yet they often overlook task constraints and user preferences.

Automated Theorem Proving Game of Go

LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks

no code implementations2 Feb 2024 Subbarao Kambhampati, Karthik Valmeekam, Lin Guan, Mudit Verma, Kaya Stechly, Siddhant Bhambri, Lucas Saldyt, Anil Murthy

On the other side are perhaps over-pessimistic claims that all that LLMs are good for in planning/reasoning tasks are as mere translators of the problem specification from one syntactic format to another, and ship the problem off to external symbolic solvers.

Theory of Mind abilities of Large Language Models in Human-Robot Interaction : An Illusion?

no code implementations10 Jan 2024 Mudit Verma, Siddhant Bhambri, Subbarao Kambhampati

In this work, we explore the task of Perceived Behavior Recognition, where a robot employs a Large Language Model (LLM) to assess the robot's generated behavior in a manner similar to human observer.

Language Modelling Large Language Model

Benchmarking Multi-Agent Preference-based Reinforcement Learning for Human-AI Teaming

no code implementations21 Dec 2023 Siddhant Bhambri, Mudit Verma, Anil Murthy, Subbarao Kambhampati

We introduce the notion of Human-Flexibility, i. e. whether the human partner is amenable to multiple team strategies, with a special case being Specified Orchestration where the human has a single team policy in mind (most constrained case).

Benchmarking reinforcement-learning

GPT-4 Doesn't Know It's Wrong: An Analysis of Iterative Prompting for Reasoning Problems

no code implementations19 Oct 2023 Kaya Stechly, Matthew Marquez, Subbarao Kambhampati

The study seems to indicate that (i) LLMs are bad at solving graph coloring instances (ii) they are no better at verifying a solution--and thus are not effective in iterative modes with LLMs critiquing LLM-generated solutions (iii) the correctness and content of the criticisms--whether by LLMs or external solvers--seems largely irrelevant to the performance of iterative prompting.

Scheduling

Can Large Language Models Really Improve by Self-critiquing Their Own Plans?

no code implementations12 Oct 2023 Karthik Valmeekam, Matthew Marquez, Subbarao Kambhampati

We evaluate a planning system that employs LLMs for both plan generation and verification.

Learning and Leveraging Verifiers to Improve Planning Capabilities of Pre-trained Language Models

no code implementations26 May 2023 Daman Arora, Subbarao Kambhampati

By randomly sampling actions from the same dataset, we generate examples of invalid actions which are then used to train a verifier which can check for action applicability.

valid

On the Planning Abilities of Large Language Models : A Critical Investigation

2 code implementations25 May 2023 Karthik Valmeekam, Matthew Marquez, Sarath Sreedharan, Subbarao Kambhampati

We aim to evaluate (1) the effectiveness of LLMs in generating plans autonomously in commonsense planning tasks and (2) the potential of LLMs in LLM-Modulo settings where they act as a source of heuristic guidance for external planners and verifiers.

Methods and Mechanisms for Interactive Novelty Handling in Adversarial Environments

no code implementations28 Feb 2023 Tung Thai, Ming Shen, Mayank Garg, Ayush Kalani, Nakul Vaidya, Utkarsh Soni, Mudit Verma, Sriram Gopalakrishnan, Neeraj Varshney, Chitta Baral, Subbarao Kambhampati, Jivko Sinapov, Matthias Scheutz

Learning to detect, characterize and accommodate novelties is a challenge that agents operating in open-world domains need to address to be able to guarantee satisfactory task performance.

Novelty Detection

A State Augmentation based approach to Reinforcement Learning from Human Preferences

no code implementations17 Feb 2023 Mudit Verma, Subbarao Kambhampati

Reinforcement Learning has suffered from poor reward specification, and issues for reward hacking even in simple enough domains.

reinforcement-learning Reinforcement Learning (RL)

Data Driven Reward Initialization for Preference based Reinforcement Learning

no code implementations17 Feb 2023 Mudit Verma, Subbarao Kambhampati

We propose a data-driven reward initialization method that does not add any additional cost to the human in the loop and negligible cost to the PbRL agent and show that doing so ensures that the predicted rewards of the initialized reward model are uniform in the state space and this reduces the variability in the performance of the method across multiple runs and is shown to improve the overall performance compared to other initialization methods.

reinforcement-learning Reinforcement Learning (RL)

Exploiting Unlabeled Data for Feedback Efficient Human Preference based Reinforcement Learning

no code implementations17 Feb 2023 Mudit Verma, Siddhant Bhambri, Subbarao Kambhampati

Preference Based Reinforcement Learning has shown much promise for utilizing human binary feedback on queried trajectory pairs to recover the underlying reward model of the Human in the Loop (HiL).

reinforcement-learning Reinforcement Learning (RL)

A Mental Model Based Theory of Trust

no code implementations29 Jan 2023 Zahra Zahedi, Sarath Sreedharan, Subbarao Kambhampati

Handling trust is one of the core requirements for facilitating effective interaction between the human and the AI agent.

AI Agent Decision Making

Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences

no code implementations28 Oct 2022 Lin Guan, Karthik Valmeekam, Subbarao Kambhampati

We propose two practical methods that can learn to model any kind of behavioral attributes from ordered behavior clips.

Advice Conformance Verification by Reinforcement Learning agents for Human-in-the-Loop

no code implementations7 Oct 2022 Mudit Verma, Ayush Kharkwal, Subbarao Kambhampati

Through our experiments, we show that our method can provide an interpretable means of solving the Advice-Conformance Verification problem by conveying whether or not the agent is using the human's advice.

Decision Making reinforcement-learning +1

A Mental-Model Centric Landscape of Human-AI Symbiosis

no code implementations18 Feb 2022 Zahra Zahedi, Sarath Sreedharan, Subbarao Kambhampati

Through this paper, we will see how this new framework allows us to capture the various works done in the space of human-AI interaction and identify the fundamental behavioral patterns supported by these works.

Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity

1 code implementation6 Feb 2022 Lin Guan, Sarath Sreedharan, Subbarao Kambhampati

At the low level, we learn a set of diverse policies for each possible task subgoal identified by the landmark, which are then stitched together.

Diversity reinforcement-learning +1

Gradient-Based Mixed Planning with Symbolic and Numeric Action Parameters

no code implementations19 Oct 2021 Kebing Jin, Hankz Hankui Zhuo, Zhanhao Xiao, Hai Wan, Subbarao Kambhampati

In this paper, we propose a novel algorithm framework to solve numeric planning problems mixed with logical relations and numeric changes based on gradient descent.

valid

Learning from Ambiguous Demonstrations with Self-Explanation Guided Reinforcement Learning

1 code implementation11 Oct 2021 Yantian Zha, Lin Guan, Subbarao Kambhampati

Our main contribution is to propose the Self-Explanation for RL from Demonstrations (SERLfD) framework, which can overcome the limitations of traditional RLfD works.

reinforcement-learning Reinforcement Learning (RL)

Symbols as a Lingua Franca for Bridging Human-AI Chasm for Explainable and Advisable AI Systems

no code implementations21 Sep 2021 Subbarao Kambhampati, Sarath Sreedharan, Mudit Verma, Yantian Zha, Lin Guan

The jury is still out on whether AI systems will need to use symbols in their internal reasoning to achieve general intelligence capabilities.

Computing Policies That Account For The Effects Of Human Agent Uncertainty During Execution In Markov Decision Processes

1 code implementation15 Sep 2021 Sriram Gopalakrishnan, Mudit Verma, Subbarao Kambhampati

We present a framework to model the human agent's behavior with respect to state uncertainty, and can be used to compute MDP policies that accounts for these problems.

Integrating Planning, Execution and Monitoring in the presence of Open World Novelties: Case Study of an Open World Monopoly Solver

no code implementations9 Jul 2021 Sriram Gopalakrishnan, Utkarsh Soni, Tung Thai, Panagiotis Lymperopoulos, Matthias Scheutz, Subbarao Kambhampati

The game of monopoly is an adversarial multi-agent domain where there is no fixed goal other than to be the last player solvent, There are useful subgoals like monopolizing sets of properties, and developing them.

Not all users are the same: Providing personalized explanations for sequential decision making problems

no code implementations23 Jun 2021 Utkarsh Soni, Sarath Sreedharan, Subbarao Kambhampati

The former is achieved by a data-driven clustering approach while for the latter, we compile our explanation generation problem into a POMDP.

Clustering Decision Making +1

GPT3-to-plan: Extracting plans from text using GPT-3

1 code implementation14 Jun 2021 Alberto Olmo, Sarath Sreedharan, Subbarao Kambhampati

Operations in many essential industries including finance and banking are often characterized by the need to perform repetitive sequential tasks.

Translation

Trust-Aware Planning: Modeling Trust Evolution in Iterated Human-Robot Interaction

no code implementations3 May 2021 Zahra Zahedi, Mudit Verma, Sarath Sreedharan, Subbarao Kambhampati

The problem of trust management is particularly challenging in mixed human-robot teams where the human and the robot may have different models about the task at hand and thus may have different expectations regarding the current course of action, thereby forcing the robot to focus on the costly explicable behavior.

Management

Planning for Proactive Assistance in Environments with Partial Observability

no code implementations2 May 2021 Anagha Kulkarni, Siddharth Srivastava, Subbarao Kambhampati

This paper addresses the problem of synthesizing the behavior of an AI agent that provides proactive task assistance to a human in settings like factory floors where they may coexist in a common environment.

AI Agent

A Unifying Bayesian Formulation of Measures of Interpretability in Human-AI

no code implementations21 Apr 2021 Sarath Sreedharan, Anagha Kulkarni, David E. Smith, Subbarao Kambhampati

Existing approaches for generating human-aware agent behaviors have considered different measures of interpretability in isolation.

Human-AI Symbiosis: A Survey of Current Approaches

no code implementations18 Mar 2021 Zahra Zahedi, Subbarao Kambhampati

In this paper, we aim at providing a comprehensive outline of the different threads of work in human-AI collaboration.

Learning Movement Strategies for Moving Target Defense

no code implementations1 Jan 2021 Sailik Sengupta, Subbarao Kambhampati

We argue that existing models are inadequate in sequential settings when there is incomplete information about rational adversary and yield sub-optimal movement strategies.

Q-Learning

Model Elicitation through Direct Questioning

no code implementations24 Nov 2020 Sachin Grover, David Smith, Subbarao Kambhampati

We show how to generate questions to refine the robot's understanding of the teammate's model.

A Bayesian Account of Measures of Interpretability in Human-AI Interaction

no code implementations22 Nov 2020 Sarath Sreedharan, Anagha Kulkarni, Tathagata Chakraborti, David E. Smith, Subbarao Kambhampati

Existing approaches for the design of interpretable agent behavior consider different measures of interpretability in isolation.

Minimizing Robot Navigation-Graph For Position-Based Predictability By Humans

no code implementations28 Oct 2020 Sriram Gopalakrishnan, Subbarao Kambhampati

In situations where humans and robots are moving in the same space whilst performing their own tasks, predictable paths taken by mobile robots can not only make the environment feel safer, but humans can also help with the navigation in the space by avoiding path conflicts or not blocking the way.

Blocking Position +1

Moving Target Defense for Robust Monitoring of Electric Grid Transformers in Adversarial Environments

1 code implementation8 Oct 2020 Sailik Sengupta, Kaustav Basu, Arunabha Sen, Subbarao Kambhampati

In this paper, we draw inspiration from work in Moving Target Defense (MTD) and consider a dynamic monitoring strategy that makes it difficult for an attacker to prevent unique identification of behavioral signals that indicate the status of HVTs.

Computer Science and Game Theory

Multi-agent Reinforcement Learning in Bayesian Stackelberg Markov Games for Adaptive Moving Target Defense

no code implementations20 Jul 2020 Sailik Sengupta, Subbarao Kambhampati

We argue that existing models are inadequate in sequential settings when there is incomplete information about a rational adversary and yield sub-optimal movement strategies.

Multi-agent Reinforcement Learning Q-Learning +1

Designing Environments Conducive to Interpretable Robot Behavior

no code implementations2 Jul 2020 Anagha Kulkarni, Sarath Sreedharan, Sarah Keren, Tathagata Chakraborti, David Smith, Subbarao Kambhampati

Given structured environments (like warehouses and restaurants), it may be possible to design the environment so as to boost the interpretability of the robot's behavior or to shape the human's expectations of the robot's behavior.

Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentation

1 code implementation NeurIPS 2021 Lin Guan, Mudit Verma, Sihang Guo, Ruohan Zhang, Subbarao Kambhampati

We focus on the task of learning from feedback, in which the human trainer not only gives binary evaluative "good" or "bad" feedback for queried state-action pairs, but also provides a visual explanation by annotating relevant features in images.

Atari Games Data Augmentation +3

The Emerging Landscape of Explainable AI Planning and Decision Making

no code implementations26 Feb 2020 Tathagata Chakraborti, Sarath Sreedharan, Subbarao Kambhampati

In this paper, we provide a comprehensive outline of the different threads of work in Explainable AI Planning (XAIP) that has emerged as a focus area in the last couple of years and contrast that with earlier efforts in the field in terms of techniques, target users, and delivery mechanisms.

Decision Making

Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable Representations

no code implementations ICLR 2022 Sarath Sreedharan, Utkarsh Soni, Mudit Verma, Siddharth Srivastava, Subbarao Kambhampati

As increasingly complex AI systems are introduced into our daily lives, it becomes important for such systems to be capable of explaining the rationale for their decisions and allowing users to contest these decisions.

Decision Making Montezuma's Revenge

Imperfect ImaGANation: Implications of GANs Exacerbating Biases on Facial Data Augmentation and Snapchat Selfie Lenses

no code implementations26 Jan 2020 Niharika Jain, Alberto Olmo, Sailik Sengupta, Lydia Manikonda, Subbarao Kambhampati

In this paper, we show that popular Generative Adversarial Networks (GANs) exacerbate biases along the axes of gender and skin tone when given a skewed distribution of face-shots.

Data Augmentation Face Generation +3

Challenges of Human-Aware AI Systems

no code implementations15 Oct 2019 Subbarao Kambhampati

From its inception, AI has had a rather ambivalent relationship to humans---swinging between their augmentation and replacement.

Learning Action Models from Disordered and Noisy Plan Traces

no code implementations26 Aug 2019 Hankz Hankui Zhuo, Jing Peng, Subbarao Kambhampati

Our approach takes as input a set of plan traces with disordered actions and noise and outputs action models that can best explain the plan traces.

Signaling Friends and Head-Faking Enemies Simultaneously: Balancing Goal Obfuscation and Goal Legibility

no code implementations25 May 2019 Anagha Kulkarni, Siddharth Srivastava, Subbarao Kambhampati

In order to be useful in the real world, AI agents need to plan and act in the presence of others, who may include adversarial and cooperative entities.

Expectation-Aware Planning: A Unifying Framework for Synthesizing and Executing Self-Explaining Plans for Human-Aware Planning

no code implementations18 Mar 2019 Sarath Sreedharan, Tathagata Chakraborti, Christian Muise, Subbarao Kambhampati

In this work, we present a new planning formalism called Expectation-Aware planning for decision making with humans in the loop where the human's expectations about an agent may differ from the agent's own model.

Decision Making

Inference of Human's Observation Strategy for Monitoring Robot's Behavior based on a Game-Theoretic Model of Trust

no code implementations1 Mar 2019 Zahra Zahedi, Sailik Sengupta, Subbarao Kambhampati

Thus, we define the concept of a trust boundary over the mixed strategy space of the human and show that it helps to discover optimal monitoring strategies.

Markov Game Modeling of Moving Target Defense for Strategic Detection of Threats in Cloud Networks

2 code implementations23 Dec 2018 Ankur Chowdhary, Sailik Sengupta, Dijiang Huang, Subbarao Kambhampati

The processing and storage of critical data in large-scale cloud networks necessitate the need for scalable security solutions.

Plan-Recognition-Driven Attention Modeling for Visual Recognition

no code implementations2 Dec 2018 Yantian Zha, Yikang Li, Tianshu Yu, Subbarao Kambhampati, Baoxin Li

We build an event recognition system, ER-PRN, which takes Pixel Dynamics Network as a subroutine, to recognize events based on observations augmented by plan-recognition-driven attention.

TGE-viz : Transition Graph Embedding for Visualization of Plan Traces and Domains

no code implementations24 Nov 2018 Sriram Gopalakrishnan, Subbarao Kambhampati

TGE-viz allows users to visualize and criticize plans more intuitively for mixed-initiative planning.

Graph Embedding

Imagining an Engineer: On GAN-Based Data Augmentation Perpetuating Biases

no code implementations9 Nov 2018 Niharika Jain, Lydia Manikonda, Alberto Olmo Hernandez, Sailik Sengupta, Subbarao Kambhampati

The use of synthetic data generated by Generative Adversarial Networks (GANs) has become quite a popular method to do data augmentation for many applications.

Data Augmentation

Extracting Action Sequences from Texts Based on Deep Reinforcement Learning

no code implementations7 Mar 2018 Wenfeng Feng, Hankz Hankui Zhuo, Subbarao Kambhampati

Extracting action sequences from natural language texts is challenging, as it requires commonsense inferences based on world knowledge.

reinforcement-learning Reinforcement Learning (RL) +1

Discovering Underlying Plans Based on Shallow Models

no code implementations4 Mar 2018 Hankz Hankui Zhuo, Yantian Zha, Subbarao Kambhampati

Specifically, we propose two approaches, DUP and RNNPlanner, to discover target plans based on vector representations of actions.

Hierarchical Expertise-Level Modeling for User Specific Robot-Behavior Explanations

no code implementations19 Feb 2018 Sarath Sreedharan, Siddharth Srivastava, Subbarao Kambhampati

There is a growing interest within the AI research community to develop autonomous systems capable of explaining their behavior to users.

Explanation Generation

A Unified Framework for Planning in Adversarial and Cooperative Environments

no code implementations16 Feb 2018 Anagha Kulkarni, Siddharth Srivastava, Subbarao Kambhampati

By slightly varying our framework, we present an approach for goal legibility in cooperative settings which produces plans that achieve a goal while being consistent with at most j goals from a set of confounding goals.

Plan Explanations as Model Reconciliation -- An Empirical Study

no code implementations3 Feb 2018 Tathagata Chakraborti, Sarath Sreedharan, Sachin Grover, Subbarao Kambhampati

Recent work in explanation generation for decision making agents has looked at how unexplained behavior of autonomous systems can be understood in terms of differences in the model of the system and the human's understanding of the same, and how the explanation process as a result of this mismatch can be then seen as a process of reconciliation of these models.

Decision Making Explanation Generation

Algorithms for the Greater Good! On Mental Modeling and Acceptable Symbiosis in Human-AI Collaboration

no code implementations30 Jan 2018 Tathagata Chakraborti, Subbarao Kambhampati

Effective collaboration between humans and AI-based systems requires effective modeling of the human in the loop, both in terms of the mental state as well as the physical capabilities of the latter.

Recognizing Plans by Learning Embeddings from Observed Action Distributions

no code implementations5 Dec 2017 Yantian Zha, Yikang Li, Sriram Gopalakrishnan, Baoxin Li, Subbarao Kambhampati

The first involves resampling the distribution sequences to single action sequences, from which we could learn an action affinity model based on learned action (word) embeddings for plan recognition.

Activity Recognition Word Embeddings

Tweeting AI: Perceptions of Lay vs Expert Twitterati

no code implementations25 Sep 2017 Lydia Manikonda, Subbarao Kambhampati

Specifically, this paper performs a comparative analysis on the understanding of users belonging to two categories -- general AI-Tweeters (AIT) and expert AI-Tweeters (EAIT) who share posts about AI on Twitter.

Emotion Recognition

Balancing Explicability and Explanation in Human-Aware Planning

no code implementations1 Aug 2017 Tathagata Chakraborti, Sarath Sreedharan, Subbarao Kambhampati

In this paper, we bring these two concepts together and show how a planner can account for both these needs and achieve a trade-off during the plan generation process itself by means of a model-space search method MEGA.

Decision Making Explanation Generation

AI Challenges in Human-Robot Cognitive Teaming

no code implementations15 Jul 2017 Tathagata Chakraborti, Subbarao Kambhampati, Matthias Scheutz, Yu Zhang

Among the many anticipated roles for robots in the future is that of being a human teammate.

MTDeep: Boosting the Security of Deep Neural Nets Against Adversarial Attacks with Moving Target Defense

1 code implementation19 May 2017 Sailik Sengupta, Tathagata Chakraborti, Subbarao Kambhampati

Present attack methods can make state-of-the-art classification systems based on deep neural networks misclassify every adversarially modified test example.

Classification General Classification

Tweeting AI: Perceptions of AI-Tweeters (AIT) vs Expert AI-Tweeters (EAIT)

no code implementations27 Apr 2017 Lydia Manikonda, Cameron Dudley, Subbarao Kambhampati

Specifically, this paper performs a comparative analysis on the understanding of users from two categories -- general AI-Tweeters (AIT) and the expert AI-Tweeters (EAIT) who share posts about AI on Twitter.

Plan Explanations as Model Reconciliation: Moving Beyond Explanation as Soliloquy

no code implementations28 Jan 2017 Tathagata Chakraborti, Sarath Sreedharan, Yu Zhang, Subbarao Kambhampati

When AI systems interact with humans in the loop, they are often called on to provide explanations for their plans and behavior.

Explicablility as Minimizing Distance from Expected Behavior

no code implementations16 Nov 2016 Anagha Kulkarni, Yantian Zha, Tathagata Chakraborti, Satya Gautam Vadlamudi, Yu Zhang, Subbarao Kambhampati

In order to have effective human-AI collaboration, it is necessary to address how the AI agent's behavior is being perceived by the humans-in-the-loop.

UbuntuWorld 1.0 LTS - A Platform for Automated Problem Solving & Troubleshooting in the Ubuntu OS

no code implementations27 Sep 2016 Tathagata Chakraborti, Kartik Talamadupula, Kshitij P. Fadnis, Murray Campbell, Subbarao Kambhampati

In this paper, we present UbuntuWorld 1. 0 LTS - a platform for developing automated technical support agents in the Ubuntu operating system.

Reinforcement Learning (RL)

Proactive Decision Support using Automated Planning

no code implementations24 Jun 2016 Satya Gautam Vadlamudi, Tathagata Chakraborti, Yu Zhang, Subbarao Kambhampati

Proactive decision support (PDS) helps in improving the decision making experience of human decision makers in human-in-the-loop planning environments.

Decision Making

Compliant Conditions for Polynomial Time Approximation of Operator Counts

no code implementations25 May 2016 Tathagata Chakraborti, Sarath Sreedharan, Sailik Sengupta, T. K. Satish Kumar, Subbarao Kambhampati

In this paper, we develop a computationally simpler version of the operator count heuristic for a particular class of domains.

Moving Target Defense for Web Applications using Bayesian Stackelberg Games

1 code implementation23 Feb 2016 Sailik Sengupta, Satya Gautam Vadlamudi, Subbarao Kambhampati, Marthony Taguinod, Adam Doupé, Ziming Zhao, Gail-Joon Ahn

We also address the issue of prioritizing vulnerabilities that when fixed, improves the security of the MTD system.

Plan Explicability and Predictability for Robot Task Planning

no code implementations25 Nov 2015 Yu Zhang, Sarath Sreedharan, Anagha Kulkarni, Tathagata Chakraborti, Hankz Hankui Zhuo, Subbarao Kambhampati

Hence, for such agents to be helpful, one important requirement is for them to synthesize plans that can be easily understood by humans.

Motion Planning Robot Task Planning

Discovering Underlying Plans Based on Distributed Representations of Actions

no code implementations18 Nov 2015 Xin Tian, Hankz Hankui Zhuo, Subbarao Kambhampati

Previous approaches either discover plans by maximally "matching" observed actions to plan libraries, assuming target plans are from plan libraries, or infer plans by executing domain models to best explain the observed actions, assuming complete domain models are available.

Plan or not: Remote Human-robot Teaming with Incomplete Task Information

no code implementations9 Dec 2014 Vignesh Narayanan, Yu Zhang, Nathaniel Mendoza, Subbarao Kambhampati

While information asymmetry can be desirable sometimes, it may also lead to the robot choosing improper actions that negatively influence the teaming performance.

Learning of Agent Capability Models with Applications in Multi-agent Planning

no code implementations4 Nov 2014 Yu Zhang, Subbarao Kambhampati

Thus far, there are two common representations of agent models: MDP based and action based, which are both based on action modeling.

Surrogate Search As a Way to Combat Harmful Effects of Ill-behaved Evaluation Functions

no code implementations1 Nov 2014 William Cushing, J. Benton, Patrick Eyerich, Subbarao Kambhampati

Recently, several researchers have found that cost-based satisficing search with A* often runs into problems.

The Metrics Matter! On the Incompatibility of Different Flavors of Replanning

no code implementations12 May 2014 Kartik Talamadupula, David E. Smith, Subbarao Kambhampati

An open question is whether these metrics are interchangeable; answering this requires a normalized comparison of the various replanning quality metrics.

Open-Ended Question Answering

A Formal Analysis of Required Cooperation in Multi-agent Planning

no code implementations22 Apr 2014 Yu Zhang, Subbarao Kambhampati

Then, by dividing the problems that require cooperation (referred to as RC problems) into two classes -- problems with heterogeneous and homogeneous agents, we aim to identify all the conditions that can cause RC in these two classes.

Synthesizing Robust Plans under Incomplete Domain Models

no code implementations NeurIPS 2013 Tuan A. Nguyen, Subbarao Kambhampati, Minh Do

In this paper, we first introduce annotations expressing the knowledge of the domain incompleteness and formalize the notion of plan robustness with respect to an incomplete domain model.

Herding the Crowd: Automated Planning for Crowdsourced Planning

no code implementations29 Jul 2013 Kartik Talamadupula, Subbarao Kambhampati

In this paper, we will argue that the automated oversight used in these systems can be viewed as a primitive automated planner, and that there are several opportunities for more sophisticated automated planning in effectively steering crowdsourced planning.

Scheduling

Action-Model Based Multi-agent Plan Recognition

no code implementations NeurIPS 2012 Hankz H. Zhuo, Qiang Yang, Subbarao Kambhampati

Previous MAPR approaches required a library of team activity sequences (team plans) be given as input.

Cannot find the paper you are looking for? You can Submit a new open access paper.