George Konidaris

Discovering Options That Minimize Average Planning Time AAAI 2025 Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces ICLR 2025 Knowledge Retention in Continual Model-Based Reinforcement Learning ICML 2025 Optimal Interactive Learning on the Job via Facility Location Planning RSS 2025 V-HOP: Visuo-Haptic 6D Object Pose Tracking RSS 2025 EPO: Hierarchical LLM Agents with Environment Preference Optimization EMNLP 2024 Language-guided Skill Learning with Temporal Variational Inference ICML 2024 Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy NeurIPS 2024 Model-based Reinforcement Learning for Parameterized Action Spaces ICML 2024 Coarse-Grained Smoothness for Reinforcement Learning in Metric Spaces AISTATS 2023 Effectively Learning Initiation Sets in Hierarchical Reinforcement Learning NeurIPS 2023 Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning ICML 2023 Meta-learning Parameterized Skills ICML 2023 Performance Bounds for Model and Policy Transfer in Hidden-parameter MDPs ICLR 2023 Q-functionals for Value-Based Continuous Control AAAI 2023 RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agents ICML 2023 Synthesizing Navigation Abstractions for Planning with Portable Manipulation Skills CoRL 2023 Autonomous Learning of Object-Centric Abstractions for High-Level Planning ICLR 2022 Effects of Data Geometry in Early Deep Learning NeurIPS 2022 Evaluation beyond Task Performance: Analyzing Concepts in AlphaZero in Hex NeurIPS 2022 Model-based Lifelong Reinforcement Learning with Bayesian Exploration NeurIPS 2022 Optimistic Initialization for Exploration in Continuous Control AAAI 2022 A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms JMLR 2021 Efficient Black-Box Planning Using Macro-Actions with Focused Effects IJCAI 2021 Learning Markov State Abstractions for Deep Reinforcement Learning NeurIPS 2021 Robustly Learning Composable Options in Deep Reinforcement Learning IJCAI 2021 Skill Discovery for Exploration and Planning using Deep Skill Graphs ICML 2021 Exploration in Reinforcement Learning with Deep Covering Options ICLR 2020 Learning Portable Representations for High-Level Planning ICML 2020 Option Discovery using Deep Skill Chaining ICLR 2020 Simultaneously Learning Transferable Symbols and Language Groundings from Perceptual Data for Instruction Following RSS 2020 Task Scoping for Efficient Planning in Open Worlds (Student Abstract) AAAI 2020 DeepMellow: Removing the Need for a Target Network in Deep Q-Learning IJCAI 2019 Discovering Options for Exploration by Minimizing Cover Time ICML 2019 Finding Options that Minimize Planning Time ICML 2019 Learning Multi-Level Hierarchies with Hindsight ICLR 2019 Learning to Generalize Kinematic Models to Novel Objects CoRL 2019 Policy and Value Transfer in Lifelong Reinforcement Learning ICML 2018 Active Exploration for Learning Symbolic Representations NeurIPS 2017 Bayesian Eigenobjects: A Unified Framework for 3D Robot Perception RSS 2017 Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes NeurIPS 2017 Constructing Abstraction Hierarchies Using a Skill-Symbol Loop IJCAI 2016 Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations IJCAI 2016 Representing and Learning Complex Object Interactions RSS 2016 Robot Motion Planning on a Chip RSS 2016 Policy Evaluation Using the Ω-Return NeurIPS 2015 Policy Search for Multi-Robot Coordination under Uncertainty RSS 2015 Symbol Acquisition for Probabilistic High-Level Planning IJCAI 2015 Active Learning of Parameterized Skills ICML 2014 Transfer in Reinforcement Learning via Shared Features JMLR 2012 TD_gamma: Re-evaluating Complex Backups in Temporal Difference Learning NeurIPS 2011 Constructing Skill Trees for Reinforcement Learning Agents from Demonstration Trajectories NeurIPS 2010 Skill Discovery in Continuous Reinforcement Learning Domains using Skill Chaining NeurIPS 2009