Melinda T. Gervasio

47 papers A* 4A 10B 2C 3Journal 15Unranked 12

Year	Rank	Type	Title / Venue / Authors
2025	—	`conf`	AI as Collaborative Partner: Rethinking Human-AI Teaming for the Real World. AAAI Spring Symposia Melinda T. Gervasio, Pedro Sequeira, Eric Yeh, Nicholas Marion, Sarah Bakst, Helen Gent
2025	J	`jnl`	Interpolative Decoding: Exploring the Spectrum of Personality Traits in LLMs. CoRR Eric Yeh, John Cadigan, Ran Chen, Dick Crouch, Melinda T. Gervasio, Dayne Freitag
2025	J	`jnl`	ToMCAT: Theory-of-Mind for Cooperative Agents in Teams via Multiagent Diffusion Policies. CoRR Pedro Sequeira, Vidyasagar Sadhu, Melinda T. Gervasio
2023	J	`jnl`	Confidence Calibration for Systems with Cascaded Predictive Modules. CoRR Yunye Gong, Yi Yao, Xiao Lin, Ajay Divakaran, Melinda T. Gervasio
2023	—	`conf`	IxDRL: A Novel Explainable Deep Reinforcement Learning Toolkit Based on Analyses of Interestingness. xAI (1) Pedro Sequeira, Melinda T. Gervasio
2023	J	`jnl`	IxDRL: A Novel Explainable Deep Reinforcement Learning Toolkit based on Analyses of Interestingness. CoRR Pedro Sequeira, Melinda T. Gervasio
2023	—	`conf`	Outcome-Guided Counterfactuals from a Jointly Trained Generative Latent Space. xAI (3) Eric Yeh, Pedro Sequeira, Jesse Hostetler, Melinda T. Gervasio
2022	J	`jnl`	A Framework for Understanding and Visualizing Strategies of RL Agents. CoRR Pedro Sequeira, Daniel Elenius, Jesse Hostetler, Melinda T. Gervasio
2022	J	`jnl`	Global and Local Analysis of Interestingness for Competency-Aware Deep Reinforcement Learning. CoRR Pedro Sequeira, Jesse Hostetler, Melinda T. Gervasio
2022	J	`jnl`	Outcome-Guided Counterfactuals for Reinforcement Learning Agents from a Jointly Trained Generative Latent Space. CoRR Eric Yeh, Pedro Sequeira, Jesse Hostetler, Melinda T. Gervasio
2021	A*	`conf`	Confidence Calibration for Domain Generalization under Covariate Shift. ICCV Yunye Gong, Xiao Lin, Yi Yao, Thomas G. Dietterich, Ajay Divakaran, Melinda T. Gervasio
2021	J	`jnl`	Confidence Calibration for Domain Generalization under Covariate Shift. CoRR Yunye Gong, Xiao Lin, Yi Yao, Thomas G. Dietterich, Ajay Divakaran, Melinda T. Gervasio
2020	J	`jnl`	Interestingness elements for explainable reinforcement learning: Understanding agents' capabilities and limitations. Artif. Intell. Pedro Sequeira, Melinda T. Gervasio
2019	—	`conf`	Interestingness Elements for Explainable Reinforcement Learning through Introspection. IUI Workshops Pedro Sequeira, Eric Yeh, Melinda T. Gervasio
2019	J	`jnl`	Interestingness Elements for Explainable Reinforcement Learning: Understanding Agents' Capabilities and Limitations. CoRR Pedro Sequeira, Melinda T. Gervasio
2018	—	`conf`	Explanation to Avert Surprise. IUI Workshops Melinda T. Gervasio, Karen L. Myers, Eric Yeh, Boone Adkins
2017	J	`jnl`	Evaluating intelligent knowledge systems: experiences with a user-adaptive assistant agent. Knowl. Inf. Syst. Pauline M. Berry, Thierry Donneau-Golencer, Khang Duong, Melinda T. Gervasio, Bart Peintner, Neil Yorke-Smith
2016	B	`conf`	Solution Authoring via Demonstration and Annotation: An Empirical Study. ICALT Karen L. Myers, Melinda T. Gervasio
2013	B	`conf`	Discovering action idioms bridging the gap between system-level events and human-level actions. VL/HCC Melinda T. Gervasio, Thomas J. Lee
2013	A	`conf`	Drill Evaluation for Training Procedural Skills. AIED Karen L. Myers, Melinda T. Gervasio, Christian Jones, Kyle McIntyre, Kellie Keifer
2012	J	`jnl`	Learning by Demonstration for a Collaborative Planning Environment. AI Mag. Karen L. Myers, Jake Kolojejchick, Carl Angiolillo, Tim Cummings, Tom Garvey, Matthew E. Gaston, Melinda T. Gervasio, Will Haines, Chris Jones, Kellie Keifer, Janette Knittel, David N. Morley, William Ommert, Scott Potter
2011	—	`ch.`	Goal-Directed Metacontrol for Integrated Procedure Learning. Metareasoning Jihie Kim, Karen L. Myers, Melinda T. Gervasio, Yolanda Gil
2011	A	`conf`	How to serve soup: interleaving demonstration and assisted editing to support nonprogrammers. IUI Melinda T. Gervasio, Will Haines, David N. Morley, Thomas J. Lee, C. Adam Overholtzer, Shahin Saadati, Aaron Spaulding
2011	C	`conf`	Learning by Demonstration Technology for Military Planning and Decision Making: A Deployment Story. IAAI Karen L. Myers, Jake Kolojejchick, Carl Angiolillo, Tim Cummings, Tom Garvey, Melinda T. Gervasio, Will Haines, Chris Jones, Janette Knittel, David N. Morley, William Ommert, Scott Potter
2011	A	`conf`	Learning to ask the right questions to help a learner learn. IUI Melinda T. Gervasio, Eric Yeh, Karen L. Myers
2011	J	`jnl`	PTIME: Personalized assistance for calendaring. ACM Trans. Intell. Syst. Technol. Pauline M. Berry, Melinda T. Gervasio, Bart Peintner, Neil Yorke-Smith
2009	C	`conf`	Evaluating User-Adaptive Systems: Lessons from Experiences with a Personalized Meeting Scheduling Assistant. IAAI Pauline M. Berry, Thierry Donneau-Golencer, Khang Duong, Melinda T. Gervasio, Bart Peintner, Neil Yorke-Smith
2009	A	`conf`	From geek to sleek: integrating task learning tools to support end users in real-world applications. IUI Aaron Spaulding, Jim Blythe, Will Haines, Melinda T. Gervasio
2009	—	`conf`	Iteration Learning by Demonstration. AAAI Spring Symposium: Agents that Learn from Human Teachers Steven Eker, Thomas J. Lee, Melinda T. Gervasio
2009	C	`conf`	Learning by Demonstration to Support Military Planning and Decision Making. IAAI Thomas D. Garvey, Melinda T. Gervasio, Thomas J. Lee, Karen L. Myers, Carl Angiolillo, Matthew E. Gaston, Janette Knittel, Jake Kolojejchick
2009	—	`conf`	Question Asking to Inform Preference Learning: A Case Study. AAAI Spring Symposium: Agents that Learn from Human Teachers Melinda T. Gervasio, Karen L. Myers, Marie desJardins, Fusun Yaman
2009	A	`conf`	What were you thinking?: filling in missing dataflow through inference in learning from demonstration. IUI Melinda T. Gervasio, Janet L. Murdock
2007	J	`jnl`	An Intelligent Personal Assistant for Task and Time Management. AI Mag. Karen L. Myers, Pauline Berry, Jim Blythe, Ken Conley, Melinda T. Gervasio, Deborah L. McGuinness, David N. Morley, Avi Pfeffer, Martha E. Pollack, Milind Tambe
2006	A	`conf`	Deploying a personalized time management agent. AAMAS Pauline Berry, Bart Peintner, Ken Conley, Melinda T. Gervasio, Tomás E. Uribe, Neil Yorke-Smith
2006	—	`conf`	Multi-Criteria Evaluation in User-Centric Distributed Scheduling Agents. AAAI Spring Symposium: Distributed Plan and Schedule Management Pauline M. Berry, Melinda T. Gervasio, Bart Peintner, Tomás E. Uribe, Neil Yorke-Smith
2005	—	`conf`	A Personalized Time Management Assistant: Research Directions. AAAI Spring Symposium: Persistent Assistants: Living and Working with AI Pauline M. Berry, Melinda T. Gervasio, Tomás E. Uribe, Martha E. Pollack, Michael D. Moffitt
2005	A	`conf`	Active preference learning for personalized calendar scheduling assistance. IUI Melinda T. Gervasio, Michael D. Moffitt, Martha E. Pollack, Joseph M. Taylor, Tomás E. Uribe
2003	A	`conf`	An adaptive stock tracker for personalized trading advice. IUI Jungsoon P. Yoo, Melinda T. Gervasio, Pat Langley
2003	A	`conf`	Personalized trading recommendation system. IUI Jungsoon P. Yoo, Melinda T. Gervasio, Pat Langley
1999	A	`conf`	Adapting to User Preferences in Crisis Response. IUI Wayne Iba, Melinda T. Gervasio
1999	A*	`conf`	Learning User Evaluation Functions for Adaptive Scheduling Assistance. ICML Melinda T. Gervasio, Wayne Iba, Pat Langley
1998	—	`conf`	Learning to Predict User Operations for Adaptive Scheduling. AAAI/IAAI Melinda T. Gervasio, Wayne Iba, Pat Langley
1994	A*	`conf`	An Incremental Learning Approach for Completable Planning. ICML Melinda T. Gervasio, Gerald DeJong
1993	J	`jnl`	Explanation-based learning for intelligent process planning. IEEE Trans. Syst. Man Cybern. Sang-Chan Park, Melinda T. Gervasio, Michael J. Shaw, Gerald DeJong
1991	—	`conf`	On Becoming Decreasingly Reactive: Learning to Deliberate Minimally. ML Steve A. Chien, Melinda T. Gervasio, Gerald DeJong
1990	A*	`conf`	Learning General Completable Reactive Plans. AAAI Melinda T. Gervasio
1989	—	`conf`	Explanation-Based Learning of Reactive Operations. ML Melinda T. Gervasio, Gerald DeJong