{"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/11","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":11,"pages_in_order":22,"rows_per_page":100,"rows":[1001,1100],"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/10","next":"/task/imitation-learning/papers/12","papers":[{"url":null,"slug":"atari-gpt-investigating-the-capabilities-of","title":"Atari-GPT: Benchmarking Multimodal Large Language Models as Low-Level Policies in Atari Games","date":"2024-08-28","arxiv_id":"2408.15950","repositories_listed":0,"syntology":null},{"url":null,"slug":"automating-deformable-gasket-assembly","title":"Automating Deformable Gasket Assembly","date":"2024-08-22","arxiv_id":"2408.12593","repositories_listed":0,"syntology":null},{"url":null,"slug":"pareto-inverse-reinforcement-learning-for","title":"Pareto Inverse Reinforcement Learning for Diverse Expert Policy Generation","date":"2024-08-22","arxiv_id":"2408.12110","repositories_listed":0,"syntology":null},{"url":null,"slug":"ace-a-cross-platform-visual-exoskeletons","title":"ACE: A Cross-Platform Visual-Exoskeletons System for Low-Cost Dexterous Teleoperation","date":"2024-08-21","arxiv_id":"2408.11805","repositories_listed":0,"syntology":null},{"url":null,"slug":"rp1m-a-large-scale-motion-dataset-for-piano","title":"RP1M: A Large-Scale Motion Dataset for Piano Playing with Bi-Manual Dexterous Robot Hands","date":"2024-08-20","arxiv_id":"2408.11048","repositories_listed":0,"syntology":null},{"url":null,"slug":"markov-balance-satisfaction-improves","title":"Markov Balance Satisfaction Improves Performance in Strictly Batch Offline Imitation Learning","date":"2024-08-17","arxiv_id":"2408.09125","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparison-of-imitation-learning-algorithms","title":"A Comparison of Imitation Learning Algorithms for Bimanual Manipulation","date":"2024-08-13","arxiv_id":"2408.06536","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-one-shot-imitation-learning","title":"Semi-Supervised One-Shot Imitation Learning","date":"2024-08-09","arxiv_id":"2408.05285","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-generative-models-in-robotics-a-survey","title":"Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrations","date":"2024-08-08","arxiv_id":"2408.04380","repositories_listed":0,"syntology":null},{"url":null,"slug":"navinact-combining-navigation-and-imitation","title":"PLANRL: A Motion Planning and Imitation Learning Framework to Bootstrap Reinforcement Learning","date":"2024-08-07","arxiv_id":"2408.04054","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-02912","title":"KOI: Accelerating Online Imitation Learning via Hybrid Key-state Guidance","date":"2024-08-06","arxiv_id":"2408.02912","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-03200","title":"Adversarial Safety-Critical Scenario Generation using Naturalistic Human Driving Priors","date":"2024-08-06","arxiv_id":"2408.03200","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-02394","title":"CMR-Agent: Learning a Cross-Modal Agent for Iterative Image-to-Point Cloud Registration","date":"2024-08-05","arxiv_id":"2408.02394","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-01366","title":"Play to the Score: Stage-Guided Dynamic Multi-Sensory Fusion for Robotic Manipulation","date":"2024-08-02","arxiv_id":"2408.01366","repositories_listed":0,"syntology":null},{"url":null,"slug":"2407-21244","title":"VITAL: Interactive Few-Shot Imitation Learning via Visual Human-in-the-Loop Corrections","date":"2024-07-30","arxiv_id":"2407.21244","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolution-of-cooperation-in-the-public-goods","title":"Evolution of cooperation in the public goods game with Q-learning","date":"2024-07-29","arxiv_id":"2407.19851","repositories_listed":0,"syntology":null},{"url":null,"slug":"recursive-introspection-teaching-language","title":"Recursive Introspection: Teaching Language Model Agents How to Self-Improve","date":"2024-07-25","arxiv_id":"2407.18219","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-imitation-learning-through-graph","title":"Offline Imitation Learning Through Graph Search and Retrieval","date":"2024-07-22","arxiv_id":"2407.15403","repositories_listed":0,"syntology":null},{"url":null,"slug":"wayex-waypoint-exploration-using-a-single","title":"WayEx: Waypoint Exploration using a Single Demonstration","date":"2024-07-22","arxiv_id":"2407.15849","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-behavior-cloning-all-you-need","title":"Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning","date":"2024-07-20","arxiv_id":"2407.15007","repositories_listed":0,"syntology":null},{"url":null,"slug":"thought-like-pro-enhancing-reasoning-of-large","title":"Thought-Like-Pro: Enhancing Reasoning of Large Language Models through Self-Driven Prolog-based Chain-of-Thought","date":"2024-07-18","arxiv_id":"2407.14562","repositories_listed":0,"syntology":null},{"url":null,"slug":"r-x-retrieval-and-execution-from-everyday","title":"R+X: Retrieval and Execution from Everyday Human Videos","date":"2024-07-17","arxiv_id":"2407.12957","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-graph-based-adversarial-imitation-learning","title":"A Graph-based Adversarial Imitation Learning Framework for Reliable & Realtime Fleet Scheduling in Urban Air Mobility","date":"2024-07-16","arxiv_id":"2407.12113","repositories_listed":0,"syntology":null},{"url":null,"slug":"bellman-diffusion-models","title":"Bellman Diffusion Models","date":"2024-07-16","arxiv_id":"2407.12163","repositories_listed":0,"syntology":null},{"url":null,"slug":"dino-pre-training-for-vision-based-end-to-end","title":"DINO Pre-training for Vision-based End-to-end Autonomous Driving","date":"2024-07-15","arxiv_id":"2407.10803","repositories_listed":0,"syntology":null},{"url":null,"slug":"global-reinforcement-learning-beyond-linear","title":"Global Reinforcement Learning: Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods","date":"2024-07-13","arxiv_id":"2407.09905","repositories_listed":0,"syntology":null},{"url":null,"slug":"pail-performance-based-adversarial-imitation","title":"PAIL: Performance based Adversarial Imitation Learning Engine for Carbon Neutral Optimization","date":"2024-07-12","arxiv_id":"2407.08910","repositories_listed":0,"syntology":null},{"url":null,"slug":"metaurban-a-simulation-platform-for-embodied","title":"MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility","date":"2024-07-11","arxiv_id":"2407.08725","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-human-like-driving-active-inference","title":"Towards Human-Like Driving: Active Inference in Autonomous Vehicle Control","date":"2024-07-10","arxiv_id":"2407.07684","repositories_listed":0,"syntology":null},{"url":null,"slug":"autoverse-an-evolvable-game-langugage-for","title":"Autoverse: An Evolvable Game Language for Learning Robust Embodied Agents","date":"2024-07-05","arxiv_id":"2407.04221","repositories_listed":0,"syntology":null},{"url":null,"slug":"bunny-visionpro-real-time-bimanual-dexterous","title":"Bunny-VisionPro: Real-Time Bimanual Dexterous Teleoperation for Imitation Learning","date":"2024-07-03","arxiv_id":"2407.03162","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-fusion-and-task-guided-embedding","title":"Efficient Fusion and Task Guided Embedding for End-to-end Autonomous Driving","date":"2024-07-03","arxiv_id":"2407.02878","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-cor-a-dual-expert-approach-to","title":"Safe CoR: A Dual-Expert Approach to Integrating Imitation Learning and Safe Reinforcement Learning Using Constraint Rewards","date":"2024-07-02","arxiv_id":"2407.02245","repositories_listed":0,"syntology":null},{"url":null,"slug":"equibot-sim-3-equivariant-diffusion-policy","title":"EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient Learning","date":"2024-07-01","arxiv_id":"2407.01479","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-television-teleoperation-with-immersive","title":"Open-TeleVision: Teleoperation with Immersive Active Visual Feedback","date":"2024-07-01","arxiv_id":"2407.01512","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-complexity-of-learning-to-cooperate","title":"On the Complexity of Learning to Cooperate with Populations of Socially Rational Agents","date":"2024-06-29","arxiv_id":"2407.00419","repositories_listed":0,"syntology":null},{"url":null,"slug":"omnijarvis-unified-vision-language-action","title":"OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents","date":"2024-06-27","arxiv_id":"2407.00114","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-state-action-reward-state-action","title":"The State-Action-Reward-State-Action Algorithm in Spatial Prisoner's Dilemma Game","date":"2024-06-25","arxiv_id":"2406.17326","repositories_listed":0,"syntology":null},{"url":null,"slug":"mereq-max-ent-residual-q-inverse-rl-for","title":"MEReQ: Max-Ent Residual-Q Inverse RL for Sample-Efficient Alignment from Intervention","date":"2024-06-24","arxiv_id":"2406.16258","repositories_listed":0,"syntology":null},{"url":null,"slug":"racil-ray-tracing-based-multi-uav-obstacle","title":"RaCIL: Ray Tracing based Multi-UAV Obstacle Avoidance through Composite Imitation Learning","date":"2024-06-24","arxiv_id":"2407.02520","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-mpc-a-dagger-driven-imitation-learning","title":"Deep-MPC: A DAGGER-Driven Imitation Learning Strategy for Optimal Constrained Battery Charging","date":"2024-06-23","arxiv_id":"2406.15985","repositories_listed":0,"syntology":null},{"url":null,"slug":"imperative-learning-a-self-supervised-neural","title":"Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomy","date":"2024-06-23","arxiv_id":"2406.16087","repositories_listed":0,"syntology":null},{"url":null,"slug":"gaussian-splatting-to-real-world-flight","title":"Gaussian Splatting to Real World Flight Navigation Transfer with Liquid Networks","date":"2024-06-21","arxiv_id":"2406.15149","repositories_listed":0,"syntology":null},{"url":null,"slug":"coohoi-learning-cooperative-human-object","title":"CooHOI: Learning Cooperative Human-Object Interaction with Manipulated Object Dynamics","date":"2024-06-20","arxiv_id":"2406.14558","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-imitation-learning-with-model-based","title":"Offline Imitation Learning with Model-based Reverse Augmentation","date":"2024-06-18","arxiv_id":"2406.12550","repositories_listed":0,"syntology":null},{"url":null,"slug":"sample-efficient-imitative-multi-token","title":"Physics-informed Imitative Reinforcement Learning for Real-world Driving","date":"2024-06-18","arxiv_id":"2407.02508","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-the-communication-gap-artificial","title":"Bridging the Communication Gap: Artificial Agents Learning Sign Language through Imitation","date":"2024-06-14","arxiv_id":"2406.10043","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-imitation-learning-for-language","title":"Contrastive Imitation Learning for Language-guided Multi-Task Robotic Manipulation","date":"2024-06-14","arxiv_id":"2406.09738","repositories_listed":0,"syntology":null},{"url":null,"slug":"primer-perception-aware-robust-learning-based","title":"PRIMER: Perception-Aware Robust Learning-based Multiagent Trajectory Planner","date":"2024-06-14","arxiv_id":"2406.10060","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-dual-approach-to-imitation-learning-from","title":"A Dual Approach to Imitation Learning from Observations with Offline Datasets","date":"2024-06-13","arxiv_id":"2406.08805","repositories_listed":0,"syntology":null},{"url":null,"slug":"cimrl-combining-imitiation-and-reinforcement","title":"CIMRL: Combining IMitation and Reinforcement Learning for Safe Autonomous Driving","date":"2024-06-13","arxiv_id":"2406.08878","repositories_listed":0,"syntology":null},{"url":null,"slug":"rile-reinforced-imitation-learning","title":"RILe: Reinforced Imitation Learning","date":"2024-06-12","arxiv_id":"2406.08472","repositories_listed":0,"syntology":null},{"url":null,"slug":"aligning-agents-like-large-language-models","title":"Aligning Agents like Large Language Models","date":"2024-06-06","arxiv_id":"2406.04208","repositories_listed":0,"syntology":null},{"url":null,"slug":"behavior-targeted-attack-on-reinforcement","title":"Behavior-Targeted Attack on Reinforcement Learning with Limited Access to Victim's Policy","date":"2024-06-06","arxiv_id":"2406.03862","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-imitation-learning-value-is-easy","title":"Multi-Agent Imitation Learning: Value is Easy, Regret is Hard","date":"2024-06-06","arxiv_id":"2406.04219","repositories_listed":0,"syntology":null},{"url":null,"slug":"robocasa-large-scale-simulation-of-everyday","title":"RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots","date":"2024-06-04","arxiv_id":"2406.02523","repositories_listed":0,"syntology":null},{"url":"/paper/learning-from-mistakes-a-weakly-supervised","slug":"learning-from-mistakes-a-weakly-supervised","title":"Validity Learning on Failures: Mitigating the Distribution Shift in Autonomous Vehicle Planning","date":"2024-06-03","arxiv_id":"2406.01544","repositories_listed":0,"syntology":null},{"url":null,"slug":"mot-a-mixture-of-actors-reinforcement","title":"MOT: A Mixture of Actors Reinforcement Learning Method by Optimal Transport for Algorithmic Trading","date":"2024-06-03","arxiv_id":"2407.01577","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-words-to-actions-unveiling-the","title":"From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems","date":"2024-05-30","arxiv_id":"2405.19883","repositories_listed":0,"syntology":null},{"url":null,"slug":"inverse-concave-utility-reinforcement","title":"Inverse Concave-Utility Reinforcement Learning is Inverse Game Theory","date":"2024-05-29","arxiv_id":"2405.19024","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-and-language-navigation-generative","title":"Vision-and-Language Navigation Generative Pretrained Transformer","date":"2024-05-27","arxiv_id":"2405.16994","repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-efficient-off-policy-adversarial","title":"Provably Efficient Off-Policy Adversarial Imitation Learning with Convergence Guarantees","date":"2024-05-26","arxiv_id":"2405.16668","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-imitation-learning-in-real-world","title":"Multi-Agent Inverse Reinforcement Learning in Real World Unstructured Pedestrian Crowds","date":"2024-05-26","arxiv_id":"2405.16439","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-reward-adversarial-imitation","title":"Diffusion-Reward Adversarial Imitation Learning","date":"2024-05-25","arxiv_id":"2405.16194","repositories_listed":0,"syntology":null},{"url":null,"slug":"amortized-nonmyopic-active-search-via-deep","title":"Amortized nonmyopic active search via deep imitation learning","date":"2024-05-23","arxiv_id":"2405.15031","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-imitation-learning-with","title":"Efficient Imitation Learning with Conservative World Models","date":"2024-05-21","arxiv_id":"2405.13193","repositories_listed":0,"syntology":null},{"url":null,"slug":"rulefuser-injecting-rules-in-evidential","title":"RuleFuser: An Evidential Bayes Approach for Rule Injection in Imitation Learned Planners and Predictors for Robustness under Distribution Shifts","date":"2024-05-18","arxiv_id":"2405.11139","repositories_listed":0,"syntology":null},{"url":null,"slug":"reducing-risk-for-assistive-reinforcement","title":"Reducing Risk for Assistive Reinforcement Learning Policies with Diffusion Models","date":"2024-05-13","arxiv_id":"2405.07603","repositories_listed":0,"syntology":null},{"url":null,"slug":"exact-an-end-to-end-autonomous-excavator","title":"ExACT: An End-to-End Autonomous Excavator System Using Action Chunking With Transformers","date":"2024-05-09","arxiv_id":"2405.05861","repositories_listed":0,"syntology":null},{"url":null,"slug":"ranking-based-client-selection-with-imitation","title":"Ranking-based Client Selection with Imitation Learning for Efficient Federated Learning","date":"2024-05-07","arxiv_id":"2405.04122","repositories_listed":0,"syntology":null},{"url":null,"slug":"robotic-constrained-imitation-learning-for","title":"Robotic Constrained Imitation Learning for the Peg Transfer Task in Fundamentals of Laparoscopic Surgery","date":"2024-05-06","arxiv_id":"2405.03440","repositories_listed":0,"syntology":null},{"url":null,"slug":"vectorpainter-a-novel-approach-to-stylized","title":"VectorPainter: Advanced Stylized Vector Graphics Synthesis Using Stroke-Style Priors","date":"2024-05-05","arxiv_id":"2405.02962","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-learning-in-discounted-linear-mdps","title":"Imitation Learning in Discounted Linear MDPs without exploration assumptions","date":"2024-05-03","arxiv_id":"2405.02181","repositories_listed":0,"syntology":null},{"url":null,"slug":"cgd-constraint-guided-diffusion-policies-for","title":"CGD: Constraint-Guided Diffusion Policies for UAV Trajectory Planning","date":"2024-05-02","arxiv_id":"2405.01758","repositories_listed":0,"syntology":null},{"url":null,"slug":"continual-imitation-learning-for-prosthetic","title":"Continual Learning from Simulated Interactions via Multitask Prospective Rehearsal for Bionic Limb Behavior Modeling","date":"2024-05-02","arxiv_id":"2405.01114","repositories_listed":0,"syntology":null},{"url":null,"slug":"intervengen-interventional-data-generation","title":"IntervenGen: Interventional Data Generation for Robust and Data-Efficient Robot Imitation Learning","date":"2024-05-02","arxiv_id":"2405.01472","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-learning-a-survey-of-learning","title":"A Survey of Imitation Learning Methods, Environments and Metrics","date":"2024-04-30","arxiv_id":"2404.19456","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-mobile-device-control-agents","title":"Benchmarking Mobile Device Control Agents across Diverse Configurations","date":"2024-04-25","arxiv_id":"2404.16660","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-privileged-information-for-dubins","title":"Distilling Privileged Information for Dubins Traveling Salesman Problems with Neighborhoods","date":"2024-04-25","arxiv_id":"2404.16721","repositories_listed":0,"syntology":null},{"url":null,"slug":"idil-imitation-learning-of-intent-driven","title":"IDIL: Imitation Learning of Intent-Driven Expert Behavior","date":"2024-04-25","arxiv_id":"2404.16989","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-air-combat-behavior-modeling","title":"A survey of air combat behavior modeling using machine learning","date":"2024-04-22","arxiv_id":"2404.13954","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-personalize-aligning-llm-planners-with","title":"LLM-Personalize: Aligning LLM Planners with Human Preferences via Reinforced Self-Training for Housekeeping Robots","date":"2024-04-22","arxiv_id":"2404.14285","repositories_listed":0,"syntology":null},{"url":null,"slug":"augmenting-safety-critical-driving-scenarios","title":"Augmenting Safety-Critical Driving Scenarios while Preserving Similarity to Expert Trajectories","date":"2024-04-20","arxiv_id":"2404.13347","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-imitation-learning-exploring-the","title":"Unveiling Imitation Learning: Exploring the Impact of Data Falsity to Large Language Model","date":"2024-04-15","arxiv_id":"2404.09717","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-imitation-learning-via-boosting","title":"Adversarial Imitation Learning via Boosting","date":"2024-04-12","arxiv_id":"2404.08513","repositories_listed":0,"syntology":null},{"url":null,"slug":"adademo-data-efficient-demonstration","title":"AdaDemo: Data-Efficient Demonstration Expansion for Generalist Robotic Agent","date":"2024-04-11","arxiv_id":"2404.07428","repositories_listed":0,"syntology":null},{"url":null,"slug":"reward-learning-from-suboptimal","title":"Reward Learning from Suboptimal Demonstrations with Applications in Surgical Electrocautery","date":"2024-04-10","arxiv_id":"2404.07185","repositories_listed":0,"syntology":null},{"url":null,"slug":"cnn-based-game-state-detection-for-a-foosball","title":"CNN-based Game State Detection for a Foosball Table","date":"2024-04-08","arxiv_id":"2404.05357","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-gil-safety-guided-imitation-learning","title":"SAFE-GIL: SAFEty Guided Imitation Learning for Robotic Systems","date":"2024-04-08","arxiv_id":"2404.05249","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompting-multi-modal-tokens-to-enhance-end","title":"Prompting Multi-Modal Tokens to Enhance End-to-End Autonomous Driving Imitation Learning with LLMs","date":"2024-04-07","arxiv_id":"2404.04869","repositories_listed":0,"syntology":null},{"url":null,"slug":"dida-denoised-imitation-learning-based-on","title":"DIDA: Denoised Imitation Learning based on Domain Adaptation","date":"2024-04-04","arxiv_id":"2404.03382","repositories_listed":0,"syntology":null},{"url":null,"slug":"sensor-imitate-third-person-expert-s","title":"SENSOR: Imitate Third-Person Expert's Behaviors via Active Sensoring","date":"2024-04-04","arxiv_id":"2404.03386","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-game-a-model-based-and-imitation","title":"Imitation Game: A Model-based and Imitation Learning Deep Reinforcement Learning Hybrid","date":"2024-04-02","arxiv_id":"2404.01794","repositories_listed":0,"syntology":null},{"url":null,"slug":"keypoint-action-tokens-enable-in-context","title":"Keypoint Action Tokens Enable In-Context Imitation Learning in Robotics","date":"2024-03-28","arxiv_id":"2403.19578","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-imitation-learning-from-multiple","title":"Offline Imitation Learning from Multiple Baselines with Applications to Compiler Optimization","date":"2024-03-28","arxiv_id":"2403.19462","repositories_listed":0,"syntology":null},{"url":null,"slug":"riemann-near-real-time-se-3-equivariant-robot","title":"RiEMann: Near Real-Time SE(3)-Equivariant Robot Manipulation without Point Cloud Segmentation","date":"2024-03-28","arxiv_id":"2403.19460","repositories_listed":0,"syntology":null},{"url":null,"slug":"lord-large-models-based-opposite-reward","title":"LORD: Large Models based Opposite Reward Design for Autonomous Driving","date":"2024-03-27","arxiv_id":"2403.18965","repositories_listed":0,"syntology":null},{"url":null,"slug":"dyna-lflh-learning-agile-navigation-in","title":"Dyna-LfLH: Learning Agile Navigation in Dynamic Environments from Learned Hallucination","date":"2024-03-25","arxiv_id":"2403.17231","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounding-language-plans-in-demonstrations","title":"Grounding Language Plans in Demonstrations Through Counterfactual Perturbations","date":"2024-03-25","arxiv_id":"2403.17124","repositories_listed":0,"syntology":null},{"url":null,"slug":"ibcb-efficient-inverse-batched-contextual","title":"IBCB: Efficient Inverse Batched Contextual Bandit for Behavioral Evolution History","date":"2024-03-24","arxiv_id":"2403.16075","repositories_listed":0,"syntology":null}],"record_sha256":"426c134aea5e61033cc69d34d3f0d5af0c34e32817597e4d8121f2942d77fcfc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}