Research Interests
Human-AI Interaction - Planning for human-robot teams and decision support, explicable planning, explanation generation for humans in the loop and value alignment.
XAI - Explanation Generation for Sequential Decision-Making Problems.
Planning and Learning - Combining planning and learning methods for more effective long term sequential decision-making.
Model-Lite Planning - Representation and learning of incomplete models for plan generation, recognition and recommendation.
Books
Dissertation
Journal Articles
Conference Papers
Expectation Alignment: Handling Reward Misspecification in the Presence of Expectation Mismatch HELP! Providing Proactive Support in the Presence of Knowledge Asymmetry. Can LLMs Fix Issues with Reasoning Models? Towards More Likely Models for AI Planning. Goal Alignment: Re-analyzing Value Alignment Problems Using Human-Aware AI. Optimistic Exploration in Reinforcement Learning Using Symbolic Model Estimates On the Planning Abilities of Large Language Models -- A Critical Investigation. Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning. PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change. Human-Aware AI – A Foundational Framework for Human-AI Interaction Generalizing Action Justification and Causal Links to Policies Planning for Attacker Entrapment in Adversarial Settings Goal Alignment: Re-analyzing Value Alignment Problems Using Human-Aware AI Trust-Aware Planning: Modeling Trust Evolution in Iterated Human-Robot Interaction Explicable or Optimal: Trust Aware Planning in Iterated Human Robot Interaction Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable Representations On the Computational Complexity of Model Reconcilation. RADAR-X: An Interactive Mixed Initiative Planning Interface Pairing Contrastive Explanations and Revised Plan Suggestions Symbols as a Lingua Franca for Bridging Human-AI Chasm for Explainable and Advisable AI Systems Not all users are the same: Providing personalized explanations for sequential decision making problems A Unifying Bayesian Formulation of Measures of Interpretability in Human-AI Interaction Designing Environments Conducive to Interpretable Robot Behavior The Emerging Landscape of Explainable AI Planning and Decision Making TLdR: Policy Summarization for Factored SSP Problems Using Temporal Abstractions. D3WA+: A Case Study of XAIP in a Model Acquisition Task . Expectation-Aware Planning: A Unifying Framework for Synthesizing and Executing Self-Explaining Plans for Human-Aware Planning Model-Free Model Reconciliation. Why Can't You Do That HAL? Explaining Unsolvability of Planning Tasks. Balancing Explicability and Explanations for Human-Aware Planning CAP: A Decision Support System for Crew Scheduling using Automated Planning Plan Explanations as Model Reconciliation – An Empirical Study Explicability? Legibility? Predictability? Transparency? Privacy? Security? The Emerging Landscape of Interpretable Agent Behavior Projection-Aware Task Planning and Execution for Human-in-the-Loop Operation of Robots in a Mixed-Reality Workspace Hierarchical Expertise Level Modeling for User Specific Contrastive Explanations Balancing Explicability and Explanations: Emergent Behaviors in Human-Aware Planning. Handling Model Uncertainty and Multiplicity in Explanations via Model Reconciliation Plan explanations as model reconciliation: Moving beyond explanation as soliloquy. Plan Explicability and Predictability for Robot Task Planning Compliant Conditions for Polynomial Time Approximation of Operator Counts. A Formal Analysis of Required Cooperation in Multi-agent Planning Capability Models and their application in Multi-agent planning.
Workshop Papers (Refereed)
A Mental-Model Centric Landscape of Human-AI Symbiosis Revisiting Value Alignment Through the Lens of Human-Aware AI Towards customizable reinforcement learning agents: Enabling preference specification through online vocabulary expansion Large Language Models Still Can't Plan (A Benchmark for LLMs on Planning and Reasoning about Change) Why Did You Do That? Generalizing Causal Link Explanations to Fully Observable Non-Deterministic Planning Problems Leveraging PDDL to Make Inscrutable Agents Interpretable: A Case for Post Hoc Symbolic Explanations for Sequential-Decision Making Problems Trust-Aware Planning: Modeling Trust Evolution in Longitudinal Human-Robot Interaction. GPT3-to-plan: Extracting plans from text using GPT-3. A Bayesian Account of Measures of Interpretability in Human-AI Interaction. RADAR-X: An Interactive Interface Pairing Contrastive Explanations with Revised Plan Suggestions. Explainable Composition of Aggregated Assistants. A General Framework for Synthesizing and Executing Self-Explaining Plans for Human-AI Interaction. Design for interpretability. Plan Explanation Through Search in an Abstract Model Space. Human-Aware Planning Revisited: A Tale of Three Models. Balancing Explicability and Explanation in Human-Aware Planning. Explanations as Model Reconciliation - A Mutli-Agent Perspective. Alternative Modes of Interaction in Proximal Human-in-the-Loop Operation of Robots. Plan Explainability and Predictability for Robot Task Planning