Why Is Charles Lee Isbell, Jr. Influential?
According to Wikipedia , Charles Lee Isbell Jr. is an American computationalist, researcher, and educator. He has been a professor in the Georgia Institute of Technology College of Computing since 2002, and since July 2019 is the John P. Imlay, Jr. Dean of the College. His research interests focus on machine learning and artificial intelligence, particularly interactive and human-centered AI. He has published over 100 scientific papers. In addition to his research work, Isbell has been an advocate for increasing access to and diversity in higher education.
Charles Lee Isbell, Jr.'s Published Works MIMIC: Finding Optima by Estimating Probability Densities (544)Policy Shaping: Integrating Human Feedback with Reinforcement Learning (235)Detection and explanation of anomalous activities: representing activities as bags of event n-grams Transfer Learning in Real-Time Strategy Games Using Hybrid CBR/RL (151)Discovering Characteristic Actions from On-Body Sensor Data A social reinforcement learning agent A novel sequence representation for unsupervised analysis of human activities Discovering Multivariate Motifs using Subsequence Density Estimation and Greedy Mixture Learning (102)Detecting Subdimensional Motifs: An Efficient Algorithm for Generalized Multivariate Pattern Discovery Restructuring Sparse High Dimensional Data for Effective Retrieval (74)Cobot in LambdaMOO: A Social Statistics Agent (73)A Survey and Qualitative Analysis of Recent Advances in Drama Management (68)Reinforcement learning for declarative optimization-based drama management Declarative optimization-based drama management in interactive fiction Improving Activity Discovery with Automatic Neighborhood Estimation (62)Exploration from Demonstration for Interactive Reinforcement Learning (60)Cobot in LambdaMOO: An Adaptive Social Statistics Agent Imitating Latent Policies from Observation (59)How Multirobot Systems Research will Accelerate our Understanding of Social Animal Behavior Environment-Independent Task Specifications via GLTL (57)Learning From Explanations Using Sentiment and Advice in RL Targeting Specific Distributions of Trajectories in MDPs (56)Policy Shaping with Human Teachers (55)A Physics-Based Model Prior for Object-Oriented MDPs (52)Fast Nonparametric Conditional Density Estimation Schema Learning: Experience-Based Construction of Predictive Action Models (46)QUIC-SVD: Fast SVD Using Cosine Trees (44)Looping suffix tree-based inference of partially observable hidden state Automatic State Abstraction from Demonstration Towards adaptive programming: integrating reinforcement learning into a programming language Description Logic in Practice: A CLASSIC Application (36)Computing Optimal Strategies to Commit to in Stochastic Games (36)Threads™: how to restructure a computer science curriculum for a flat world Cobot: A Social Reinforcement Learning Agent (34)Ishmail: Immediate Identification of Important Information (34)Point Based Value Iteration with Optimal Belief Compression for Dec-POMDPs (31)From devices to tasks: automatic task prediction for personalized appliance control (Re)defining computing curricula by (re)defining computing Unsupervised Activity Discovery and Characterization From Event-Streams (30)Real Time Voice Processing with Audiovisual Feedback: Toward Autonomous Agents with Perfect Pitch (28)Solving Stochastic Games (28)Object focused q-learning for autonomous agents Fast kernel conditional density estimation: A dual-tree Monte Carlo approach Learning to Influence Emotional Responses for Interactive Storytelling (24)Learning to Compose Skills (24)Discovering options from example trajectories A globally optimal algorithm for TTD-MDPs Tree-Independent Dual-Tree Algorithms (23)Automatic task decomposition and state abstraction from demonstration (22)Authorial Idioms for Target Distributions in TTD-MDPs (22)On the Difficulty of Modular Reinforcement Learning for Real-World Partial Programming (22)Comparing end-user and intelligent remote control interface generation An IP Continuum for Adaptive Interface Design (20)The Unexpected Pedagogical Benefits of Making Higher Education Accessible Desiderata for Managers of Interactive Experiences : A Survey of Recent Advances in Drama Management (18)Abstraction from demonstration for efficient reinforcement learning in high-dimensional domains The Parallel Problems Server: A Client-Server Model for Interactive Large Scale Scientific Computation Learning Options through Human Interaction (17)Autonomous nondeterministic tour guides: improving quality of experience with TTD-MDPs Quick Polytope Approximation of All Correlated Equilibria in Stochastic Games (16)Declarative Optimization-Based Drama Management ( DODM ) in the Interactive Fiction Anchorhead (15)Markov Games of Incomplete Information for Multi-Agent Reinforcement Learning (15)State Aware Imitation Learning (15)Batch versus interactive learning by demonstration Using influence and persuasion to shape player experiences Beyond Adversarial: The Case for Game AI as Storytelling (13)Perceptual Reward Functions (13)Supporting routine decision-making with a next-generation alarm clock Using training regimens to teach expanding function approximators How A . I . and multi-robot systems research will accelerate our understanding of social animal behavior (12)Player Autonomy versus Designer Intent: A Case Study of Interactive Tour Guides (11)Ultrafast Monte Carlo for kernel estimators and generalized statistical summations (11)Estimating Player Satisfaction Through the Author ’ s Eyes (11)Reasoning with Black Boxes: Handling Test Concepts in CLASSIC (10)Navigation Among Movable Obstacles with learned dynamic constraints Learning non-holonomic object models for mobile manipulation CobotDS: a spoken dialogue system for chat (9)Composable Modular Reinforcement Learning Master's at Scale: Five Years in a Scalable Online Graduate Degree Lessons on Using Computationally Generated Influence for Shaping Narrative Experiences Five Years of Graduate CS Education Online and at Scale Learning executable agent behaviors from observation DEXTOR: Reduced Effort Authoring for Template-Based Natural Language Generation (7)Cross-Domain Perceptual Reward Functions (7)Estimating Q(s, s') with Deep Deterministic Dynamics Gradients (7)Using Feature Value Distributions to Estimate Player Satisfaction through an Author's Eyes (7)Rising CS Enrollments: Meeting the Challenges A description logic-based configurator on the web Policy Shaping in Domains with Multiple Optimal Policies: (Extended Abstract) (6)Interactive Supercomputing with PPMatlab (6)Ultrafast Monte Carlo for Statistical Summations (6)Peer Reviewing Short Answers using Comparative Judgement On the Use of Computational Models of Influence for Managing Interactive Virtual Experiences Impact of user context on song selection Activity Discovery : Sparse Motifs from Multivariate Time Series (5)Computing Stackelberg strategies in stochastic games Deriving Behavior from Personality : A Reinforcement Learning Approach (4)Universal Value Density Estimation for Imitation Learning and Goal-Conditioned Reinforcement Learning (4)MITMatlab: A Tool for Interactive Supercomputing (4)Object-Focused Advice in Reinforcement Learning (4)Explorations of the practical issues of learning prediction-control tasks using temporal difference learning methods Interactive Supercomputing with MITMatlab (3)The Parallel Problems Server: an Interactive Tool for Large Scale Machine Learning (3)Perceptual Values from Observation (3)A Bayesian Framework for Nash Equilibrium Inference in Human-Robot Parallel Play Optimization problems involving collections of dependent objects MotifMark: Finding Regulatory Motifs in DNA Sequences Towards automatic personalization of device controls An Architecture for Supporting Personalized Agents in Appliance Interaction (3)Supportive Actions for Manipulation in Human-Robot Coworker Teams On the use of Computational Models of Influence for Interactive Virtual Experience Management (3)Randomized Local Search as Successive Estimation of Probability Densities (2)Purely Geometric Scene Association and Retrieval - A Case for Macro Scale 3D Geometry (2)A decision-theoretic approach to file consistency in constrained peer-to-peer device networks Discovery, Evaluation, and Exploration of Human Supplied Options and Constraints (2)Managing Domain Knowledge and Multiple Models with Boosting (2)Horizon-based Value Iteration (2)State Space Decomposition and Subgoal Creation for Transfer in Deep Reinforcement Learning (2)Who speaks for AI? Story similarity measures for drama management with ttd-mdps (2)Ask Me Anything about MOOCs Boosting Diverse Learners for Domain Agnostic Time Series Classification (2)User modeling for personalized universal appliance interaction Opportunities for Machine Learning to Impact Interactive Narrative (2)Sparse multi-level representations for text retrieval (2)MotifMark: Finding regulatory motifs in DNA sequences AAAI-2002 Fall Symposium Series DSL Design for Reinforcement Learning Agents (1)Combining function approximation, human teachers, and training regimens for real-world RL (1)Expressing Tasks Robustly via Multiple Discount Factors (1)Accord: Middleware Support for Contextual, Ubiquitous Data Management on User Devices (1)Reports of the AAAI 2010 Conference Workshops Pattern Discovery for Locating Motifs in Multivariate , Real-valued Time-series Data (0)Estimating Q(s,s') with Deterministic Dynamics Gradients (0)HARD ATTENTION CONTROL BY MUTUAL INFORMA- (0)Personalized agents : papers from the 2002 AAAI Fall Symposium, November 15-17, North Falmouth, Massachusetts (0)Dimensionality Reduction for Improved Source Separation in FMRI Data Topic-Centered Multi-Level Representations for Text Retrieval (0)Hard Attention Control By Mutual Information Maximization (0)Exploiting Training Regimens to Improve Learning (0)MEAD (A Modeling Environment for Atmospheric Discovery) (0)Deconvolution of component map time courses for task related activation discovery (0)CPATH EAE: Extending contextualized computing in multiple institutions using threads (0)Towards adaptive programming: integrating reinforcement learning into a programming language Mining Contexts from an Application ’ s Interaction History (0)Toward a Unified Framework for Inference of Hidden State under Partial Observability (0)Partial signal extraction for mobile media players Multi-Stage Monte Carlo Approximation for Fast Generalized Data Summations (0)Policy Shaping from Simulated Critique in Domains with Multiple Optimal Policies (0)Transferring Agent Behaviors from Videos via Motion GANs (0)More Papers This paper list is powered by the following services:
Other Resources About Charles Lee Isbell, Jr. What Schools Are Affiliated With Charles Lee Isbell, Jr.? Charles Lee Isbell, Jr. is affiliated with the following schools:
Charles Lee Isbell, Jr.'s AcademicInfluence.com Rankings
