{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/imitation-learning/papers/10","list_of":"/task/imitation-learning","task":"Imitation Learning","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":10,"pages_in_order":22,"rows_per_page":100,"rows":[901,1000],"of":2122,"counts":{"archive_papers_tagged":2122,"with_a_code_link":691,"where_syntology_ran_a_sample":234,"not_listed_spam_title":0,"listed":2122,"listed_where_code_ran":234,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":191,"every_run_a_failure_of_syntologys_instrument":43,"listed_with_a_run_with_no_instrument_failure":191,"listed_every_run_a_failure_of_syntologys_instrument":43,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/imitation-learning","prev":"/task/imitation-learning/papers/9","next":"/task/imitation-learning/papers/11","papers":[{"url":null,"slug":"sorrel-suboptimal-demonstration-guided","title":"SORREL: Suboptimal-Demonstration-Guided Reinforcement Learning for Learning to Branch","date":"2024-12-20","arxiv_id":"2412.15534","repositories_listed":0,"syntology":null},{"url":null,"slug":"adacred-adaptive-causal-decision-transformers","title":"AdaCred: Adaptive Causal Decision Transformers with Feature Crediting","date":"2024-12-19","arxiv_id":"2412.15427","repositories_listed":0,"syntology":null},{"url":null,"slug":"dream-to-manipulate-compositional-world","title":"Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination","date":"2024-12-19","arxiv_id":"2412.14957","repositories_listed":0,"syntology":null},{"url":null,"slug":"inference-aware-fine-tuning-for-best-of-n","title":"Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models","date":"2024-12-18","arxiv_id":"2412.15287","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-decorator-model-agnostic-online","title":"Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model","date":"2024-12-18","arxiv_id":"2412.13630","repositories_listed":0,"syntology":null},{"url":null,"slug":"robomind-benchmark-on-multi-embodiment","title":"RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation","date":"2024-12-18","arxiv_id":"2412.13877","repositories_listed":0,"syntology":null},{"url":null,"slug":"auto-bidding-in-real-time-auctions-via-oracle","title":"Auto-bidding in real-time auctions via Oracle Imitation Learning (OIL)","date":"2024-12-16","arxiv_id":"2412.11434","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-novel-skills-from-language-generated","title":"Learning Novel Skills from Language-Generated Demonstrations","date":"2024-12-12","arxiv_id":"2412.09286","repositories_listed":0,"syntology":null},{"url":null,"slug":"student-informed-teacher-training","title":"Student-Informed Teacher Training","date":"2024-12-12","arxiv_id":"2412.09149","repositories_listed":0,"syntology":null},{"url":null,"slug":"tidybot-an-open-source-holonomic-mobile","title":"TidyBot++: An Open-Source Holonomic Mobile Manipulator for Robot Learning","date":"2024-12-11","arxiv_id":"2412.10447","repositories_listed":0,"syntology":null},{"url":null,"slug":"swarm-behavior-cloning","title":"Swarm Behavior Cloning","date":"2024-12-10","arxiv_id":"2412.07617","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-note-on-sample-complexity-of-interactive","title":"A Note on Sample Complexity of Interactive Imitation Learning with Log Loss","date":"2024-12-09","arxiv_id":"2412.07057","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-agnostic-rl-offline-rl-and-online-rl","title":"Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone","date":"2024-12-09","arxiv_id":"2412.06685","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-soft-driving-constraints-from","title":"Learning Soft Driving Constraints from Vectorized Scene Embeddings while Imitating Expert Trajectories","date":"2024-12-07","arxiv_id":"2412.05717","repositories_listed":0,"syntology":null},{"url":null,"slug":"rl-zero-zero-shot-language-to-behaviors","title":"RLZero: Direct Policy Inference from Language Without In-Domain Supervision","date":"2024-12-07","arxiv_id":"2412.05718","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-s-the-move-hybrid-imitation-learning-via","title":"What's the Move? Hybrid Imitation Learning via Salient Points","date":"2024-12-06","arxiv_id":"2412.05426","repositories_listed":0,"syntology":null},{"url":null,"slug":"variable-speed-teaching-playback-as-real","title":"Variable-Speed Teaching-Playback as Real-World Data Augmentation for Imitation Learning","date":"2024-12-04","arxiv_id":"2412.03252","repositories_listed":0,"syntology":null},{"url":null,"slug":"lmact-a-benchmark-for-in-context-imitation","title":"LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations","date":"2024-12-02","arxiv_id":"2412.01441","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantization-aware-imitation-learning-for","title":"Quantization-Aware Imitation-Learning for Resource-Efficient Robotic Control","date":"2024-12-02","arxiv_id":"2412.01034","repositories_listed":0,"syntology":null},{"url":null,"slug":"armor-egocentric-perception-for-humanoid","title":"ARMOR: Egocentric Perception for Humanoid Robot Collision Avoidance and Motion Planning","date":"2024-11-30","arxiv_id":"2412.00396","repositories_listed":0,"syntology":null},{"url":null,"slug":"prediction-with-action-visual-policy-learning","title":"Prediction with Action: Visual Policy Learning via Joint Denoising Process","date":"2024-11-27","arxiv_id":"2411.18179","repositories_listed":0,"syntology":null},{"url":null,"slug":"unpacking-the-individual-components-of","title":"Unpacking the Individual Components of Diffusion Policy","date":"2024-11-27","arxiv_id":"2412.00084","repositories_listed":0,"syntology":null},{"url":null,"slug":"lhpf-look-back-the-history-and-plan-for-the","title":"LHPF: Look back the History and Plan for the Future in Autonomous Driving","date":"2024-11-26","arxiv_id":"2411.17253","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-reconfiguration-strategies-for-space","title":"Self-reconfiguration Strategies for Space-distributed Spacecraft","date":"2024-11-26","arxiv_id":"2411.17137","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatially-visual-perception-for-end-to-end","title":"Spatially Visual Perception for End-to-End Robotic Learning","date":"2024-11-26","arxiv_id":"2411.17458","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-steering-for-autonomous-vehicles","title":"End-to-End Steering for Autonomous Vehicles via Conditional Imitation Co-Learning","date":"2024-11-25","arxiv_id":"2411.16131","repositories_listed":0,"syntology":null},{"url":null,"slug":"rocoda-counterfactual-data-augmentation-for","title":"RoCoDA: Counterfactual Data Augmentation for Data-Efficient Robot Learning from Demonstrations","date":"2024-11-25","arxiv_id":"2411.16959","repositories_listed":0,"syntology":null},{"url":null,"slug":"wildlma-long-horizon-loco-manipulation-in-the","title":"WildLMa: Long Horizon Loco-Manipulation in the Wild","date":"2024-11-22","arxiv_id":"2411.15131","repositories_listed":0,"syntology":null},{"url":null,"slug":"error-feedback-model-for-output-correction-in","title":"Error-Feedback Model for Output Correction in Bilateral Control-Based Imitation Learning","date":"2024-11-19","arxiv_id":"2411.12255","repositories_listed":0,"syntology":null},{"url":null,"slug":"instant-policy-in-context-imitation-learning","title":"Instant Policy: In-Context Imitation Learning via Graph Diffusion","date":"2024-11-19","arxiv_id":"2411.12633","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-the-resource-gap-deploying-advanced","title":"Bridging the Resource Gap: Deploying Advanced Imitation Learning Models onto Affordable Embedded Platforms","date":"2024-11-18","arxiv_id":"2411.11406","repositories_listed":0,"syntology":null},{"url":null,"slug":"approximated-variational-bayesian-inverse","title":"Approximated Variational Bayesian Inverse Reinforcement Learning for Large Language Model Alignment","date":"2024-11-14","arxiv_id":"2411.09341","repositories_listed":0,"syntology":null},{"url":null,"slug":"robot-see-robot-do-imitation-reward-for-noisy","title":"Robot See, Robot Do: Imitation Reward for Noisy Financial Environments","date":"2024-11-13","arxiv_id":"2411.08637","repositories_listed":0,"syntology":null},{"url":null,"slug":"emperror-a-flexible-generative-perception","title":"EMPERROR: A Flexible Generative Perception Error Model for Probing Self-Driving Planners","date":"2024-11-12","arxiv_id":"2411.07719","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-learning-from-observations-an","title":"Imitation Learning from Observations: An Autoregressive Mixture of Experts Approach","date":"2024-11-12","arxiv_id":"2411.08232","repositories_listed":0,"syntology":null},{"url":null,"slug":"navigation-with-qphil-quantizing-planner-for","title":"Navigation with QPHIL: Quantizing Planner for Hierarchical Implicit Q-Learning","date":"2024-11-12","arxiv_id":"2411.07760","repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-differential-patient-care-through","title":"Identifying Differential Patient Care Through Inverse Intent Inference","date":"2024-11-11","arxiv_id":"2411.07372","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-from-diverse-behaviors-wasserstein","title":"Imitation from Diverse Behaviors: Wasserstein Quality Diversity Imitation Learning with Single-Step Archive Exploration","date":"2024-11-11","arxiv_id":"2411.06965","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-laws-for-pre-training-agents-and","title":"Scaling Laws for Pre-training Agents and World Models","date":"2024-11-07","arxiv_id":"2411.04434","repositories_listed":0,"syntology":null},{"url":null,"slug":"et-seed-efficient-trajectory-level-se-3","title":"ET-SEED: Efficient Trajectory-Level SE(3) Equivariant Diffusion Policy","date":"2024-11-06","arxiv_id":"2411.03990","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-and-contact-point-tracking-in","title":"Object and Contact Point Tracking in Demonstrations Using 3D Gaussian Splatting","date":"2024-11-05","arxiv_id":"2411.03555","repositories_listed":0,"syntology":null},{"url":null,"slug":"out-of-distribution-recovery-with-object","title":"Out-of-Distribution Recovery with Object-Centric Keypoint Inverse Policy for Visuomotor Imitation Learning","date":"2024-11-05","arxiv_id":"2411.03294","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-active-imitation-learning-with","title":"Efficient Active Imitation Learning with Random Network Distillation","date":"2024-11-04","arxiv_id":"2411.01894","repositories_listed":0,"syntology":null},{"url":null,"slug":"so-you-think-you-can-scale-up-autonomous","title":"So You Think You Can Scale Up Autonomous Robot Data Collection?","date":"2024-11-04","arxiv_id":"2411.01813","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-imitation-learning-based-optimal-energy","title":"Safe Imitation Learning-based Optimal Energy Storage Systems Dispatch in Distribution Networks","date":"2024-11-01","arxiv_id":"2411.00995","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-vitac-learning-fine-grained-manipulation","title":"3D-ViTac: Learning Fine-Grained Manipulation with Visuo-Tactile Sensing","date":"2024-10-31","arxiv_id":"2410.24091","repositories_listed":0,"syntology":null},{"url":null,"slug":"dexmimicgen-automated-data-generation-for","title":"DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning","date":"2024-10-31","arxiv_id":"2410.24185","repositories_listed":0,"syntology":null},{"url":null,"slug":"state-and-context-dependent-robotic","title":"State- and context-dependent robotic manipulation and grasping via uncertainty-aware imitation learning","date":"2024-10-31","arxiv_id":"2410.24035","repositories_listed":0,"syntology":null},{"url":null,"slug":"incremental-learning-of-retrievable-skills","title":"Incremental Learning of Retrievable Skills For Efficient Continual Task Adaptation","date":"2024-10-30","arxiv_id":"2410.22658","repositories_listed":0,"syntology":null},{"url":null,"slug":"keypoint-abstraction-using-large-models-for","title":"Keypoint Abstraction using Large Models for Object-Relative Imitation Learning","date":"2024-10-30","arxiv_id":"2410.23254","repositories_listed":0,"syntology":null},{"url":null,"slug":"softctrl-soft-conservative-kl-control-of","title":"SoftCTRL: Soft conservative KL-control of Transformer Reinforcement Learning for Autonomous Driving","date":"2024-10-30","arxiv_id":"2410.22752","repositories_listed":0,"syntology":null},{"url":null,"slug":"precise-and-dexterous-robotic-manipulation","title":"Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning","date":"2024-10-29","arxiv_id":"2410.21845","repositories_listed":0,"syntology":null},{"url":null,"slug":"deploying-ten-thousand-robots-scalable","title":"Deploying Ten Thousand Robots: Scalable Imitation Learning for Lifelong Multi-Agent Path Finding","date":"2024-10-28","arxiv_id":"2410.21415","repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-selections-for-unsupervised","title":"Identifying Selections for Unsupervised Subtask Discovery","date":"2024-10-28","arxiv_id":"2410.21616","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-the-role-of-expert-guidance-a","title":"Unveiling the Role of Expert Guidance: A Comparative Analysis of User-centered Imitation Learning and Traditional Reinforcement Learning","date":"2024-10-28","arxiv_id":"2410.21403","repositories_listed":0,"syntology":null},{"url":null,"slug":"ghil-glue-hierarchical-control-with-filtered","title":"GHIL-Glue: Hierarchical Control with Filtered Subgoal Images","date":"2024-10-26","arxiv_id":"2410.20018","repositories_listed":0,"syntology":null},{"url":null,"slug":"miles-making-imitation-learning-easy-with","title":"MILES: Making Imitation Learning Easy with Self-Supervision","date":"2024-10-25","arxiv_id":"2410.19693","repositories_listed":0,"syntology":null},{"url":null,"slug":"skillmimicgen-automated-demonstration","title":"SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deployment","date":"2024-10-24","arxiv_id":"2410.18907","repositories_listed":0,"syntology":null},{"url":null,"slug":"spire-synergistic-planning-imitation-and","title":"SPIRE: Synergistic Planning, Imitation, and Reinforcement Learning for Long-Horizon Manipulation","date":"2024-10-23","arxiv_id":"2410.18065","repositories_listed":0,"syntology":null},{"url":null,"slug":"diverse-policies-recovering-via-pointwise","title":"Diverse Policies Recovering via Pointwise Mutual Information Weighted Imitation Learning","date":"2024-10-21","arxiv_id":"2410.15910","repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-weight-diffusion-generating-policies","title":"Latent Weight Diffusion: Generating reactive policies instead of trajectories","date":"2024-10-17","arxiv_id":"2410.14040","repositories_listed":0,"syntology":null},{"url":null,"slug":"ddil-improved-diffusion-distillation-with","title":"DDIL: Diversity Enhancing Diffusion Distillation With Imitation Learning","date":"2024-10-15","arxiv_id":"2410.11971","repositories_listed":0,"syntology":null},{"url":null,"slug":"ilaeda-an-imitation-learning-based-approach","title":"ILAEDA: An Imitation Learning Based Approach for Automatic Exploratory Data Analysis","date":"2024-10-15","arxiv_id":"2410.11276","repositories_listed":0,"syntology":null},{"url":null,"slug":"arcap-collecting-high-quality-human","title":"ARCap: Collecting High-quality Human Demonstrations for Robot Learning with Augmented Reality Feedback","date":"2024-10-11","arxiv_id":"2410.08464","repositories_listed":0,"syntology":null},{"url":null,"slug":"conformalized-interactive-imitation-learning","title":"Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedback","date":"2024-10-11","arxiv_id":"2410.08852","repositories_listed":0,"syntology":null},{"url":null,"slug":"mastering-contact-rich-tasks-by-combining","title":"Mastering Contact-rich Tasks by Combining Soft and Rigid Robotics with Imitation Learning","date":"2024-10-10","arxiv_id":"2410.07787","repositories_listed":0,"syntology":null},{"url":null,"slug":"uniq-offline-inverse-q-learning-for-avoiding","title":"UNIQ: Offline Inverse Q-learning for Avoiding Undesirable Demonstrations","date":"2024-10-10","arxiv_id":"2410.08307","repositories_listed":0,"syntology":null},{"url":null,"slug":"furelise-capturing-and-physically","title":"FürElise: Capturing and Physically Synthesizing Hand Motions of Piano Performance","date":"2024-10-08","arxiv_id":"2410.05791","repositories_listed":0,"syntology":null},{"url":null,"slug":"quality-diversity-imitation-learning","title":"Quality Diversity Imitation Learning","date":"2024-10-08","arxiv_id":"2410.06151","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-imitation-from-observation","title":"Diffusion Imitation from Observation","date":"2024-10-07","arxiv_id":"2410.05429","repositories_listed":0,"syntology":null},{"url":null,"slug":"he-drive-human-like-end-to-end-driving-with","title":"HE-Drive: Human-Like End-to-End Driving with Vision Language Models","date":"2024-10-07","arxiv_id":"2410.05051","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-sample-complexity-of-a-policy-gradient","title":"On the Sample Complexity of a Policy Gradient Algorithm with Occupancy Approximation for General Utility Reinforcement Learning","date":"2024-10-05","arxiv_id":"2410.04108","repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-action-priors-from-a-single-gait-cycle","title":"Latent Action Priors for Locomotion with Deep Reinforcement Learning","date":"2024-10-04","arxiv_id":"2410.03246","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-control-informed-learning","title":"Online Control-Informed Learning","date":"2024-10-04","arxiv_id":"2410.03924","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-offline-imitation-learning-from","title":"Robust Offline Imitation Learning from Diverse Auxiliary Data","date":"2024-10-04","arxiv_id":"2410.03626","repositories_listed":0,"syntology":null},{"url":null,"slug":"seal-semantic-augmented-imitation-learning","title":"SEAL: SEmantic-Augmented Imitation Learning via Language Model","date":"2024-10-03","arxiv_id":"2410.02231","repositories_listed":0,"syntology":null},{"url":null,"slug":"canvas-commonsense-aware-navigation-system","title":"CANVAS: Commonsense-Aware Navigation System for Intuitive Human-Robot Interaction","date":"2024-10-02","arxiv_id":"2410.01273","repositories_listed":0,"syntology":null},{"url":null,"slug":"effective-tuning-strategies-for-generalist","title":"Effective Tuning Strategies for Generalist Robot Manipulation Policies","date":"2024-10-02","arxiv_id":"2410.01220","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-sample-complexity-of-imitation","title":"Improved Sample Complexity of Imitation Learning for Barrier Model Predictive Control","date":"2024-10-01","arxiv_id":"2410.00859","repositories_listed":0,"syntology":null},{"url":null,"slug":"m2distill-multi-modal-distillation-for","title":"M2Distill: Multi-Modal Distillation for Lifelong Imitation Learning","date":"2024-09-30","arxiv_id":"2410.00064","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalizability-of-graph-neural-networks-for","title":"Generalizability of Graph Neural Networks for Decentralized Unlabeled Motion Planning","date":"2024-09-29","arxiv_id":"2409.19829","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-strategy-representation-for","title":"Learning Strategy Representation for Imitation Learning in Multi-Agent Games","date":"2024-09-28","arxiv_id":"2409.19363","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-spectrum-efficiency-in-6g-satellite","title":"Enhancing Spectrum Efficiency in 6G Satellite Networks: A GAIL-Powered Policy Learning via Asynchronous Federated Inverse Reinforcement Learning","date":"2024-09-27","arxiv_id":"2409.18718","repositories_listed":0,"syntology":null},{"url":null,"slug":"good-data-is-all-imitation-learning-needs","title":"Good Data Is All Imitation Learning Needs","date":"2024-09-26","arxiv_id":"2409.17605","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-covariate-shift-in-imitation-2","title":"Mitigating Covariate Shift in Imitation Learning for Autonomous Vehicles Using Latent Space Generative World Models","date":"2024-09-25","arxiv_id":"2409.16663","repositories_listed":0,"syntology":null},{"url":null,"slug":"candere-coach-reinforcement-learning-from","title":"CANDERE-COACH: Reinforcement Learning from Noisy Feedback","date":"2024-09-23","arxiv_id":"2409.15521","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-diverse-robot-striking-motions-with","title":"Learning Diverse Robot Striking Motions with Diffusion Models and Kinematically Constrained Gradient Guidance","date":"2024-09-23","arxiv_id":"2409.15528","repositories_listed":0,"syntology":null},{"url":null,"slug":"racer-rich-language-guided-failure-recovery","title":"RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning","date":"2024-09-23","arxiv_id":"2409.14674","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-cost-whole-body-teleoperation-for-mobile","title":"Whole-Body Teleoperation for Mobile Manipulation at Zero Added Cost","date":"2024-09-23","arxiv_id":"2409.15095","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamo-in-domain-dynamics-pretraining-for","title":"DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control","date":"2024-09-18","arxiv_id":"2409.12192","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalized-robot-learning-framework","title":"Generalized Robot Learning Framework","date":"2024-09-18","arxiv_id":"2409.12061","repositories_listed":0,"syntology":null},{"url":null,"slug":"imrl-integrating-visual-physical-temporal-and","title":"IMRL: Integrating Visual, Physical, Temporal, and Geometric Representations for Enhanced Food Acquisition","date":"2024-09-18","arxiv_id":"2409.12092","repositories_listed":0,"syntology":null},{"url":null,"slug":"interact-inter-dependency-aware-action","title":"InterACT: Inter-dependency Aware Action Chunking with Hierarchical Attention Transformers for Bimanual Manipulation","date":"2024-09-12","arxiv_id":"2409.07914","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-perspective-on-ai-guided-molecular","title":"A Perspective on AI-Guided Molecular Simulations in VR: Exploring Strategies for Imitation Learning in Hyperdimensional Molecular Systems","date":"2024-09-11","arxiv_id":"2409.07189","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-analysis-of-logit-learning-with-the-r","title":"An Analysis of Logit Learning with the r-Lambert Function","date":"2024-09-08","arxiv_id":"2409.05044","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-prevalence-of-neural-collapse-in-neural","title":"The Prevalence of Neural Collapse in Neural Multivariate Regression","date":"2024-09-06","arxiv_id":"2409.04180","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-imitation-learning-motion-planner-for","title":"Hybrid Imitation-Learning Motion Planner for Urban Driving","date":"2024-09-04","arxiv_id":"2409.02871","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitating-language-via-scalable-inverse","title":"Imitating Language via Scalable Inverse Reinforcement Learning","date":"2024-09-02","arxiv_id":"2409.01369","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-reinforcement-learning-from-human","title":"Preference-Based Multi-Agent Reinforcement Learning: Data Coverage and Algorithmic Techniques","date":"2024-09-01","arxiv_id":"2409.00717","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-without-human-feedback","title":"Reinforcement Learning without Human Feedback for Last Mile Fine-Tuning of Large Language Models","date":"2024-08-29","arxiv_id":"2408.16753","repositories_listed":0,"syntology":null}],"record_sha256":"ca4c7cadf5797d6591336d8e0fdc98d938f66583952242d10012bda3428be846","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}