{"total":51,"rows":[{"id":"2104.05859","title":"Rapid Exploration for Open-World Navigation with Latent Goal Models","created":"2021-04-12","cited_by_count":121,"area":null},{"id":"2103.01937","title":"Neural Production Systems: Learning Rule-Governed Visual Dynamics","created":"2021-03-02","cited_by_count":75,"area":null},{"id":"2210.17444","title":"Multimodal Information Bottleneck: Learning Minimal Sufficient Unimodal and Multimodal Representations","created":"2022-10-31","cited_by_count":48,"area":null},{"id":"2203.12677","title":"Vision-Based Manipulators Need to Also See from Their Hands","created":"2022-03-15","cited_by_count":47,"area":null},{"id":"2112.09899","title":"Improving Subgraph Recognition with Variational Graph Information Bottleneck","created":"2021-12-18","cited_by_count":45,"area":null},{"id":"2203.17138","title":"Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviors","created":"2022-03-31","cited_by_count":30,"area":null},{"id":"2109.03214","title":"Robust Predictable Control","created":"2021-09-07","cited_by_count":29,"area":null},{"id":"2103.11155","title":"Recognizing Predictive Substructures with Subgraph Information Bottleneck","created":"2021-03-20","cited_by_count":28,"area":null},{"id":"2109.14509","title":"PAC-Bayes Information Bottleneck","created":"2021-09-29","cited_by_count":28,"area":null},{"id":"2111.03189","title":"Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning","created":"2021-11-04","cited_by_count":26,"area":null},{"id":"2311.04193","title":"Selective Visual Representations Improve Convergence and Generalization for Embodied AI","created":"2023-11-07","cited_by_count":19,"area":null},{"id":"2212.12809","title":"Understanding the Complexity Gains of Single-Task RL with a Curriculum","created":"2022-12-24","cited_by_count":17,"area":null},{"id":"2103.12300","title":"Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Exploration","created":"2021-03-23","cited_by_count":15,"area":null},{"id":"2110.12997","title":"Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning","created":"2021-10-25","cited_by_count":15,"area":null},{"id":"2205.14794","title":"Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning","created":"2022-05-30","cited_by_count":13,"area":null},{"id":"2212.13835","title":"Representation Learning in Deep RL via Discrete Information Bottleneck","created":"2022-12-28","cited_by_count":13,"area":null},{"id":"2211.00247","title":"Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning","created":"2022-11-01","cited_by_count":11,"area":null},{"id":"2305.17109","title":"Reinforcement Learning with Simple Sequence Priors","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2309.03130","title":"MyoDex: A Generalizable Prior for Dexterous Manipulation","created":"2023-09-06","cited_by_count":11,"area":null},{"id":"2101.04178","title":"Action Priors for Large Action Spaces in Robotics","created":"2021-01-11","cited_by_count":10,"area":null},{"id":"2209.01947","title":"MO2: Model-Based Offline Options","created":"2022-09-05","cited_by_count":10,"area":null},{"id":"2312.02203","title":"Learning High-Order Relationships of Brain Regions","created":"2023-12-02","cited_by_count":10,"area":null},{"id":"2208.03848","title":"Information bottleneck theory of high-dimensional regression: relevancy, efficiency and optimality","created":"2022-08-08","cited_by_count":9,"area":null},{"id":"2102.04881","title":"Measuring Progress in Deep Reinforcement Learning Sample Efficiency","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2111.02994","title":"Towards an Understanding of Default Policies in Multitask Policy Optimization","created":"2021-11-04","cited_by_count":8,"area":null},{"id":"2103.02957","title":"Toward Robust Long Range Policy Transfer","created":"2021-03-04","cited_by_count":6,"area":null},{"id":"2105.13977","title":"Perturbation Theory for the Information Bottleneck","created":"2021-05-28","cited_by_count":6,"area":null},{"id":"2201.08300","title":"From Psychological Curiosity to Artificial Curiosity: Curiosity-Driven Learning in Artificial Intelligence Tasks","created":"2022-01-20","cited_by_count":6,"area":null},{"id":"2302.12617","title":"Leveraging Jumpy Models for Planning and Fast Learning in Robotic Domains","created":"2023-02-24","cited_by_count":6,"area":null},{"id":"2401.16236","title":"Effective Communication with Dynamic Feature Compression","created":"2024-01-29","cited_by_count":6,"area":null},{"id":"2509.19292","title":"SOE: Sample-Efficient Robot Policy Self-Improvement via On-Manifold Exploration","created":"2025-09-23","cited_by_count":6,"area":null},{"id":"2203.05724","title":"Information-Theoretic Odometry Learning","created":"2022-03-11","cited_by_count":5,"area":null},{"id":"2204.12620","title":"Rate-Constrained Remote Contextual Bandits","created":"2022-04-26","cited_by_count":5,"area":null},{"id":"2306.05991","title":"Approximate information state based convergence analysis of recurrent Q-learning","created":"2023-06-09","cited_by_count":5,"area":null},{"id":"2305.03263","title":"Bayesian Reinforcement Learning with Limited Cognitive Load","created":"2023-05-05","cited_by_count":4,"area":null},{"id":"2307.11373","title":"Offline Diversity Maximization Under Imitation Constraints","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2201.08115","title":"Priors, Hierarchy, and Information Asymmetry for Skill Transfer in Reinforcement Learning","created":"2022-01-20","cited_by_count":3,"area":null},{"id":"2301.05901","title":"Semantic and Effective Communication for Remote Control Tasks with Dynamic Feature Compression","created":"2023-01-14","cited_by_count":3,"area":null},{"id":"2106.06621","title":"Piecewise-constant Neural ODEs","created":"2021-06-11","cited_by_count":2,"area":null},{"id":"2303.17762","title":"Generalized Information Bottleneck for Gaussian Variables","created":"2023-03-31","cited_by_count":2,"area":null},{"id":"2403.00869","title":"Enhancing Multivariate Time Series Forecasting with Mutual Information-driven Cross-Variable and Temporal Modeling","created":"2024-03-01","cited_by_count":2,"area":null},{"id":"2509.21805","title":"Towards Minimal Causal Representations for Human Multimodal Language Understanding","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2101.01883","title":"Off-Policy Meta-Reinforcement Learning Based on Feature Embedding Spaces","created":"2021-01-06","cited_by_count":1,"area":null},{"id":"2509.01804","title":"Mixture of Balanced Information Bottlenecks for Long-Tailed Visual Recognition","created":"2025-09-01","cited_by_count":1,"area":null},{"id":"2511.01444","title":"Robust Multimodal Sentiment Analysis via Double Information Bottleneck","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2109.08677","title":"Realistic PointGoal Navigation via Auxiliary Losses and Information Bottleneck","created":"2021-09-17","cited_by_count":0,"area":null},{"id":"2112.10374","title":"CGIBNet: Bandwidth-constrained Communication with Graph Information Bottleneck in Multi-Agent Reinforcement Learning","created":"2021-12-20","cited_by_count":0,"area":null},{"id":"2205.10607","title":"Coordinating Policies Among Multiple Agents via an Intelligent Communication Channel","created":"2022-05-21","cited_by_count":0,"area":null},{"id":"2207.08258","title":"Minimum Description Length Control","created":"2022-07-17","cited_by_count":0,"area":null},{"id":"2308.15063","title":"Learning Cross-modality Information Bottleneck Representation for Heterogeneous Person Re-Identification","created":"2023-08-29","cited_by_count":0,"area":null},{"id":"2606.06123","title":"Adaptive state-action abstractions via rate-distortion","created":"2026-06-04","cited_by_count":0,"area":null}],"next_cursor":null}