{"total":105,"rows":[{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221,"area":null},{"id":"2106.05819","title":"Adversarial Graph Augmentation to Improve Graph Contrastive Learning","created":"2021-06-10","cited_by_count":200,"area":null},{"id":"1905.12888","title":"Imitation Learning as $f$-Divergence Minimization","created":"2019-05-30","cited_by_count":123,"area":"offlinerl"},{"id":"2102.13185","title":"Off-Policy Imitation Learning from Observations","created":"2021-02-25","cited_by_count":70,"area":"offlinerl"},{"id":"1909.09314","title":"Meta-Inverse Reinforcement Learning with Probabilistic Context Variables","created":"2019-09-20","cited_by_count":50,"area":"offlinerl"},{"id":"2104.02862","title":"Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification","created":"2021-04-07","cited_by_count":50,"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":"1910.04417","title":"Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement","created":"2019-10-10","cited_by_count":46,"area":"offlinerl"},{"id":"1910.01077","title":"Task-Relevant Adversarial Imitation Learning","created":"2019-10-02","cited_by_count":45,"area":"offlinerl"},{"id":"2112.09899","title":"Improving Subgraph Recognition with Variational Graph Information Bottleneck","created":"2021-12-18","cited_by_count":45,"area":null},{"id":"1911.00459","title":"Positive-Unlabeled Reward Learning","created":"2019-11-01","cited_by_count":37,"area":"alignment"},{"id":"2006.15061","title":"Intrinsic Reward Driven Imitation Learning via Generative Model","created":"2020-06-26","cited_by_count":35,"area":"offlinerl"},{"id":"2311.02496","title":"LocoMuJoCo: A Comprehensive Imitation Learning Benchmark for Locomotion","created":"2023-11-04","cited_by_count":33,"area":"offlinerl"},{"id":"2303.00599","title":"LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning","created":"2023-03-01","cited_by_count":29,"area":"offlinerl"},{"id":"2103.11155","title":"Recognizing Predictive Substructures with Subgraph Information Bottleneck","created":"2021-03-20","cited_by_count":28,"area":null},{"id":"2202.13110","title":"Optimal-er Auctions through Attention","created":"2022-02-26","cited_by_count":27,"area":null},{"id":"1810.10593","title":"Inverse reinforcement learning for video games","created":"2018-10-24","cited_by_count":26,"area":"offlinerl"},{"id":"2108.06908","title":"Online Multi-Granularity Distillation for GAN Compression","created":"2021-08-16","cited_by_count":24,"area":null},{"id":"2103.05079","title":"Domain-Robust Visual Imitation Learning with Mutual Information Constraints","created":"2021-03-08","cited_by_count":20,"area":"offlinerl"},{"id":"2110.08729","title":"VoteHMR: Occlusion-Aware Voting Network for Robust 3D Human Mesh Recovery from Partial Point Clouds","created":"2021-10-17","cited_by_count":18,"area":null},{"id":"2309.00082","title":"RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability","created":"2023-08-31","cited_by_count":18,"area":null},{"id":"2105.09637","title":"Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation","created":"2021-05-20","cited_by_count":17,"area":null},{"id":"2207.00244","title":"Discriminator-Guided Model-Based Offline Imitation Learning","created":"2022-07-01","cited_by_count":17,"area":"offlinerl"},{"id":"2411.09891","title":"Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation","created":"2024-11-15","cited_by_count":17,"area":"offlinerl"},{"id":"2404.19456","title":"A Survey of Imitation Learning Methods, Environments and Metrics","created":"2024-04-30","cited_by_count":16,"area":"offlinerl"},{"id":"2006.16785","title":"Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning","created":"2020-06-28","cited_by_count":15,"area":"offlinerl"},{"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":"2103.04677","title":"Behavior-Driven Synthesis of Human Dynamics","created":"2021-03-08","cited_by_count":14,"area":null},{"id":"2202.07600","title":"Bayesian Imitation Learning for End-to-End Mobile Manipulation","created":"2022-02-15","cited_by_count":14,"area":"offlinerl"},{"id":"2006.03503","title":"Wasserstein Distance guided Adversarial Imitation Learning with Reward Shape Exploration","created":"2020-06-05","cited_by_count":13,"area":"offlinerl"},{"id":"2107.03851","title":"Imitation by Predicting Observations","created":"2021-07-08","cited_by_count":13,"area":"offlinerl"},{"id":"2403.02116","title":"Inf2Guard: An Information-Theoretic Framework for Learning Privacy-Preserving Representations against Inference Attacks","created":"2024-03-04","cited_by_count":13,"area":"safety"},{"id":"1909.06769","title":"VILD: Variational Imitation Learning with Diverse-quality Demonstrations","created":"2019-09-15","cited_by_count":12,"area":"offlinerl"},{"id":"2310.05422","title":"Reward-Consistent Dynamics Models are Strongly Generalizable for Offline Reinforcement Learning","created":"2023-10-09","cited_by_count":12,"area":"offlinerl"},{"id":"2204.11446","title":"Imitation Learning from Observations under Transition Model Disparity","created":"2022-04-25","cited_by_count":11,"area":"offlinerl"},{"id":"2306.10695","title":"SeMAIL: Eliminating Distractors in Visual Imitation via Separated Models","created":"2023-06-19","cited_by_count":10,"area":"offlinerl"},{"id":"2312.02203","title":"Learning High-Order Relationships of Brain Regions","created":"2023-12-02","cited_by_count":10,"area":null},{"id":"2108.06530","title":"Neuron Campaign for Initialization Guided by Information Bottleneck Theory","created":"2021-08-14","cited_by_count":9,"area":null},{"id":"2305.06807","title":"Information Design in Multi-Agent Reinforcement Learning","created":"2023-05-08","cited_by_count":9,"area":null},{"id":"2406.13214","title":"Self-Explainable Temporal Graph Networks based on Graph Information Bottleneck","created":"2024-06-19","cited_by_count":9,"area":null},{"id":"2502.20750","title":"Mitigating Hallucinations in Large Vision-Language Models by Adaptively Constraining Information Flow","created":"2025-02-28","cited_by_count":9,"area":"mllm"},{"id":"2005.01138","title":"Off-Policy Adversarial Inverse Reinforcement Learning","created":"2020-05-03","cited_by_count":8,"area":"offlinerl"},{"id":"2109.05940","title":"Cross Domain Robot Imitation with Invariant Representation","created":"2021-09-13","cited_by_count":8,"area":"offlinerl"},{"id":"2408.06536","title":"A Comparison of Imitation Learning Algorithms for Bimanual Manipulation","created":"2024-08-13","cited_by_count":8,"area":"offlinerl"},{"id":"2209.10149","title":"Goal-Aware Generative Adversarial Imitation Learning from Imperfect Demonstration for Robotic Cloth Manipulation","created":"2022-09-21","cited_by_count":7,"area":"offlinerl"},{"id":"1909.03773","title":"Imitation Learning from Pixel-Level Demonstrations by HashReward","created":"2019-09-09","cited_by_count":6,"area":"offlinerl"},{"id":"2102.11905","title":"Grounded Relational Inference: Domain Knowledge Driven Explainable Autonomous Driving","created":"2021-02-23","cited_by_count":6,"area":null},{"id":"2207.01708","title":"Disentangled Action Recognition with Knowledge Bases","created":"2022-07-04","cited_by_count":6,"area":null},{"id":"2106.09159","title":"Automatic Curricula via Expert Demonstrations","created":"2021-06-16","cited_by_count":5,"area":"offlinerl"},{"id":"2206.00238","title":"Transferable Reward Learning by Dynamics-Agnostic Discriminator Ensemble","created":"2022-06-01","cited_by_count":5,"area":"offlinerl"},{"id":"2306.08419","title":"Mediated Multi-Agent Reinforcement Learning","created":"2023-06-14","cited_by_count":5,"area":null},{"id":"2412.03949","title":"Learning Speed-Adaptive Walking Agent Using Imitation Learning with Physics-Informed Simulation","created":"2024-12-05","cited_by_count":5,"area":"offlinerl"},{"id":"2412.07544","title":"Contractive Dynamical Imitation Policies for Efficient Out-of-Sample Recovery","created":"2024-12-10","cited_by_count":5,"area":"offlinerl"},{"id":"2503.10626","title":"NIL: No-data Imitation Learning by Leveraging Pre-trained Video Diffusion Models","created":"2025-03-13","cited_by_count":5,"area":"diffusion"},{"id":"2505.15217","title":"Multimodal Conditional Information Bottleneck for Generalizable AI-Generated Image Detection","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"1911.07027","title":"On Value Discrepancy of Imitation Learning","created":"2019-11-16","cited_by_count":4,"area":"offlinerl"},{"id":"2211.00024","title":"A robust estimator of mutual information for deep learning interpretability","created":"2022-10-31","cited_by_count":4,"area":null},{"id":"2307.16227","title":"InfoStyler: Disentanglement Information Bottleneck for Artistic Style Transfer","created":"2023-07-30","cited_by_count":4,"area":null},{"id":"2410.06151","title":"Diversifying Policy Behaviors with Extrinsic Behavioral Curiosity","created":"2024-10-08","cited_by_count":4,"area":"offlinerl"},{"id":"1903.07854","title":"Hindsight Generative Adversarial Imitation Learning","created":"2019-03-19","cited_by_count":3,"area":"offlinerl"},{"id":"2206.09548","title":"Variational Distillation for Multi-View Learning","created":"2022-06-20","cited_by_count":3,"area":null},{"id":"2206.11299","title":"Latent Policies for Adversarial Imitation Learning","created":"2022-06-22","cited_by_count":3,"area":"offlinerl"},{"id":"2302.06271","title":"Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning","created":"2023-02-13","cited_by_count":3,"area":"offlinerl"},{"id":"2307.02829","title":"Policy Contrastive Imitation Learning","created":"2023-07-06","cited_by_count":3,"area":"offlinerl"},{"id":"2410.23680","title":"Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment","created":"2024-10-31","cited_by_count":3,"area":"offlinerl"},{"id":"2412.11066","title":"Learning Robust and Privacy-Preserving Representations via Information Theory","created":"2024-12-15","cited_by_count":3,"area":null},{"id":"2506.05688","title":"Voice Impression Control in Zero-Shot TTS","created":"2025-06-06","cited_by_count":3,"area":null},{"id":"2510.09222","title":"FM-IRL: Flow-Matching for Reward Modeling and Policy Regularization in Reinforcement Learning","created":"2025-10-10","cited_by_count":3,"area":"diffusion"},{"id":"2512.09101","title":"Masked Generative Policy for Robotic Control","created":"2025-12-09","cited_by_count":3,"area":"offlinerl"},{"id":"2606.01672","title":"RDA: Reward Design Agent for Reinforcement Learning","created":"2026-06-01","cited_by_count":3,"area":"agents"},{"id":"2104.06600","title":"GAN-Based Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback","created":"2021-04-14","cited_by_count":2,"area":"offlinerl"},{"id":"2202.04827","title":"Bias-Eliminated Semantic Refinement for Any-Shot Learning","created":"2022-02-10","cited_by_count":2,"area":null},{"id":"2405.14020","title":"Unlearning Information Bottleneck: Machine Unlearning of Systematic Patterns and Biases","created":"2024-05-22","cited_by_count":2,"area":"safety"},{"id":"2406.05510","title":"Representation Learning with Conditional Information Flow Maximization","created":"2024-06-08","cited_by_count":2,"area":null},{"id":"2507.00808","title":"Multi-interaction TTS toward professional recording reproduction","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2603.27944","title":"Flip Stunts on Bicycle Robots using Iterative Motion Imitation","created":"2026-03-30","cited_by_count":2,"area":"deeprl"},{"id":"2209.05239","title":"$\\beta$-CapsNet: Learning Disentangled Representation for CapsNet by Information Bottleneck","created":"2022-09-12","cited_by_count":1,"area":null},{"id":"2312.05405","title":"Guaranteed Trust Region Optimization via Two-Phase KL Penalization","created":"2023-12-08","cited_by_count":1,"area":null},{"id":"2402.11367","title":"Multi Task Inverse Reinforcement Learning for Common Sense Reward","created":"2024-02-17","cited_by_count":1,"area":"offlinerl"},{"id":"2407.11658","title":"Exciting Action: Investigating Efficient Exploration for Learning Musculoskeletal Humanoid Locomotion","created":"2024-07-16","cited_by_count":1,"area":null},{"id":"2411.07372","title":"Identifying Differential Patient Care Through Inverse Intent Inference","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2506.02396","title":"Towards Explicit Geometry-Reflectance Collaboration for Generalized LiDAR Segmentation in Adverse Weather","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2506.20307","title":"Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration","created":"2025-06-25","cited_by_count":1,"area":"offlinerl"},{"id":"2509.15932","title":"The Alignment Bottleneck","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2510.20165","title":"IB-GAN: Disentangled Representation Learning with Information Bottleneck Generative Adversarial Networks","created":"2025-10-23","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":"1909.03200","title":"Mature GAIL: Imitation Learning for Low-level and High-dimensional Input using Global Encoder and Cost Transformation","created":"2019-09-07","cited_by_count":0,"area":"offlinerl"},{"id":"2002.01059","title":"Preventing Imitation Learning with Adversarial Policy Ensembles","created":"2020-01-31","cited_by_count":0,"area":"offlinerl"},{"id":"2104.14379","title":"Learning Robust Variational Information Bottleneck with Reference","created":"2021-04-29","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":"2210.00637","title":"Benign Autoencoders","created":"2022-10-02","cited_by_count":0,"area":null},{"id":"2302.01193","title":"Imitating careful experts to avoid catastrophic events","created":"2023-02-02","cited_by_count":0,"area":null},{"id":"2303.07846","title":"Sample-efficient Adversarial Imitation Learning","created":"2023-03-14","cited_by_count":0,"area":"offlinerl"},{"id":"2306.01731","title":"PAGAR: Taming Reward Misalignment in Inverse Reinforcement Learning-Based Imitation Learning with Protagonist Antagonist Guided Adversarial Reward","created":"2023-06-02","cited_by_count":0,"area":"offlinerl"},{"id":"2308.09189","title":"Regularizing Adversarial Imitation Learning Using Causal Invariance","created":"2023-08-17","cited_by_count":0,"area":"offlinerl"},{"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":"2311.06438","title":"Controllability-Constrained Deep Network Models for Enhanced Control of Dynamical Systems","created":"2023-11-11","cited_by_count":0,"area":null},{"id":"2502.02867","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","created":"2025-02-05","cited_by_count":0,"area":"offlinerl"},{"id":"2605.11020","title":"Trust Region Inverse Reinforcement Learning: Explicit Dual Ascent using Local Policy Updates","created":"2026-05-10","cited_by_count":0,"area":"offlinerl"}],"next_cursor":"100"}