{"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/13","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":13,"pages_in_order":22,"rows_per_page":100,"rows":[1201,1300],"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/12","next":"/task/imitation-learning/papers/14","papers":[{"url":null,"slug":"enhanced-generalization-through","title":"Enhanced Generalization through Prioritization and Diversity in Self-Imitation Reinforcement Learning over Procedural Environments with Sparse Rewards","date":"2023-11-01","arxiv_id":"2311.00426","repositories_listed":0,"syntology":null},{"url":null,"slug":"addressing-limitations-of-state-aware","title":"Addressing Limitations of State-Aware Imitation Learning for Autonomous Driving","date":"2023-10-31","arxiv_id":"2310.20650","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-visual-navigation-of","title":"Deep Learning for Visual Navigation of Underwater Robots","date":"2023-10-30","arxiv_id":"2310.19495","repositories_listed":0,"syntology":null},{"url":null,"slug":"guided-data-augmentation-for-offline","title":"Guided Data Augmentation for Offline Reinforcement Learning and Imitation Learning","date":"2023-10-27","arxiv_id":"2310.18247","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-based-runtime-monitoring-with","title":"Model-Based Runtime Monitoring with Interactive Imitation Learning","date":"2023-10-26","arxiv_id":"2310.17552","repositories_listed":0,"syntology":null},{"url":null,"slug":"mimictouch-learning-human-s-control-strategy","title":"MimicTouch: Leveraging Multi-modal Human Tactile Demonstrations for Contact-rich Manipulation","date":"2023-10-25","arxiv_id":"2310.16917","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-traffic-simulation-a","title":"Data-driven Traffic Simulation: A Comprehensive Review","date":"2023-10-24","arxiv_id":"2310.15975","repositories_listed":0,"syntology":null},{"url":null,"slug":"good-better-best-self-motivated-imitation","title":"Good Better Best: Self-Motivated Imitation Learning for noisy Demonstrations","date":"2023-10-24","arxiv_id":"2310.15815","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-in-the-loop-task-and-motion-planning","title":"Human-in-the-Loop Task and Motion Planning for Imitation Learning","date":"2023-10-24","arxiv_id":"2310.16014","repositories_listed":0,"syntology":null},{"url":null,"slug":"webwise-web-interface-control-and-sequential","title":"WebWISE: Web Interface Control and Sequential Exploration with Large Language Models","date":"2023-10-24","arxiv_id":"2310.16042","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-makes-it-ok-to-set-a-fire-iterative-self","title":"What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations","date":"2023-10-24","arxiv_id":"2310.15431","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-generalizable-manipulation-policies","title":"Learning Generalizable Manipulation Policies with Object-Centric 3D Representations","date":"2023-10-22","arxiv_id":"2310.14386","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-discern-imitating-heterogeneous","title":"Learning to Discern: Imitating Heterogeneous Human Demonstrations with Preference and Representation Learning","date":"2023-10-22","arxiv_id":"2310.14196","repositories_listed":0,"syntology":null},{"url":null,"slug":"promoting-generalization-for-exact-solvers","title":"Promoting Generalization for Exact Solvers via Adversarial Instance Augmentation","date":"2023-10-22","arxiv_id":"2310.14161","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-visual-imitation-learning-with-inverse","title":"Robust Visual Imitation Learning with Inverse Dynamics Representations","date":"2023-10-22","arxiv_id":"2310.14274","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-in-context-imitation-learning-via","title":"Few-Shot In-Context Imitation Learning via Implicit Graph Alignment","date":"2023-10-18","arxiv_id":"2310.12238","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-shot-imitation-learning-a-pose-estimation","title":"One-Shot Imitation Learning: A Pose Estimation Perspective","date":"2023-10-18","arxiv_id":"2310.12077","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-online-learning-with-offline","title":"Efficient Online Learning with Offline Datasets for Infinite Horizon MDPs: A Bayesian Approach","date":"2023-10-17","arxiv_id":"2310.11531","repositories_listed":0,"syntology":null},{"url":null,"slug":"mimicking-the-maestro-exploring-the-efficacy","title":"Mimicking the Maestro: Exploring the Efficacy of a Virtual AI Teacher in Fine Motor Skill Acquisition","date":"2023-10-16","arxiv_id":"2310.10280","repositories_listed":0,"syntology":null},{"url":null,"slug":"progressively-efficient-learning","title":"Progressively Efficient Learning","date":"2023-10-13","arxiv_id":"2310.13004","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-episodic-curriculum-for-transformer","title":"Cross-Episodic Curriculum for Transformer Agents","date":"2023-10-12","arxiv_id":"2310.08549","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-intrinsic-optimization-intrisic","title":"Generative Intrinsic Optimization: Intrinsic Control with Model Learning","date":"2023-10-12","arxiv_id":"2310.08100","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextualized-policy-recovery-modeling-and","title":"Contextualized Policy Recovery: Modeling and Interpreting Medical Decisions with Adaptive Imitation Learning","date":"2023-10-11","arxiv_id":"2310.07918","repositories_listed":0,"syntology":null},{"url":null,"slug":"inverse-factorized-q-learning-for-cooperative","title":"Inverse Factorized Q-Learning for Cooperative Multi-agent Imitation Learning","date":"2023-10-10","arxiv_id":"2310.06801","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-transfer-in-imitation-learning","title":"Zero-Shot Transfer in Imitation Learning","date":"2023-10-10","arxiv_id":"2310.06710","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitator-learning-achieve-out-of-the-box","title":"Imitator Learning: Achieve Out-of-the-Box Imitation Ability in Variable Environments","date":"2023-10-09","arxiv_id":"2310.05712","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-consistent-neural-networks-for","title":"Memory-Consistent Neural Networks for Imitation Learning","date":"2023-10-09","arxiv_id":"2310.06171","repositories_listed":0,"syntology":null},{"url":null,"slug":"tail-task-specific-adapters-for-imitation","title":"TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models","date":"2023-10-09","arxiv_id":"2310.05905","repositories_listed":0,"syntology":null},{"url":null,"slug":"blending-imitation-and-reinforcement-learning","title":"Blending Imitation and Reinforcement Learning for Robust Policy Improvement","date":"2023-10-03","arxiv_id":"2310.01737","repositories_listed":0,"syntology":null},{"url":null,"slug":"stamp-differentiable-task-and-motion-planning","title":"STAMP: Differentiable Task and Motion Planning via Stein Variational Gradient Descent","date":"2023-10-03","arxiv_id":"2310.01775","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-learning-from-observation-through","title":"Imitation Learning from Observation through Optimal Transport","date":"2023-10-02","arxiv_id":"2310.01632","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-dag-discovery-for-interpretable","title":"Interpretable Imitation Learning with Dynamic Causal Relations","date":"2023-09-30","arxiv_id":"2310.00489","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-decentralized-flocking-controllers","title":"Learning Decentralized Flocking Controllers with Spatio-Temporal Graph Neural Network","date":"2023-09-29","arxiv_id":"2309.17437","repositories_listed":0,"syntology":null},{"url":null,"slug":"casil-cognizing-and-imitating-skills-via-a","title":"CasIL: Cognizing and Imitating Skills via a Dual Cognition-Action Architecture","date":"2023-09-28","arxiv_id":"2309.16299","repositories_listed":0,"syntology":null},{"url":null,"slug":"infer-and-adapt-bipedal-locomotion-reward","title":"Infer and Adapt: Bipedal Locomotion Reward Learning from Demonstrations via Inverse Reinforcement Learning","date":"2023-09-28","arxiv_id":"2309.16074","repositories_listed":0,"syntology":null},{"url":null,"slug":"symbolic-imitation-learning-from-black-box-to","title":"Symbolic Imitation Learning: From Black-Box to Explainable Driving Policies","date":"2023-09-27","arxiv_id":"2309.16025","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-imitation-learning-for","title":"Hierarchical Imitation Learning for Stochastic Environments","date":"2023-09-25","arxiv_id":"2309.14003","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-bandwidth-estimation-from-offline","title":"Offline to Online Learning for Real-Time Bandwidth Estimation","date":"2023-09-23","arxiv_id":"2309.13481","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-generalization-in-game-agents-with","title":"Improving Generalization in Game Agents with Data Augmentation in Imitation Learning","date":"2023-09-22","arxiv_id":"2309.12815","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-drive-anywhere","title":"Learning to Drive Anywhere","date":"2023-09-21","arxiv_id":"2309.12295","repositories_listed":0,"syntology":null},{"url":null,"slug":"c-cdot-ase-learning-conditional-adversarial","title":"C$\\cdot$ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characters","date":"2023-09-20","arxiv_id":"2309.11351","repositories_listed":0,"syntology":null},{"url":null,"slug":"cloud-based-hierarchical-imitation-learning","title":"Cloud-Based Hierarchical Imitation Learning for Scalable Transfer of Construction Skills from Human Workers to Assisting Robots","date":"2023-09-20","arxiv_id":"2309.11619","repositories_listed":0,"syntology":null},{"url":null,"slug":"privileged-to-predicted-towards-sensorimotor","title":"Privileged to Predicted: Towards Sensorimotor Reinforcement Learning for Urban Driving","date":"2023-09-18","arxiv_id":"2309.09756","repositories_listed":0,"syntology":null},{"url":null,"slug":"q-transformer-scalable-offline-reinforcement","title":"Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions","date":"2023-09-18","arxiv_id":"2309.10150","repositories_listed":0,"syntology":null},{"url":null,"slug":"naturalistic-robot-arm-trajectory-generation","title":"Naturalistic Robot Arm Trajectory Generation via Representation Learning","date":"2023-09-14","arxiv_id":"2309.07550","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-matters-to-enhance-traffic-rule","title":"What Matters to Enhance Traffic Rule Compliance of Imitation Learning for End-to-End Autonomous Driving","date":"2023-09-14","arxiv_id":"2309.07808","repositories_listed":0,"syntology":null},{"url":null,"slug":"dissipative-imitation-learning-for-discrete","title":"Dissipative Imitation Learning for Discrete Dynamic Output Feedback Control with Sparse Data Sets","date":"2023-09-13","arxiv_id":"2309.06658","repositories_listed":0,"syntology":null},{"url":null,"slug":"reboot-reuse-data-for-bootstrapping-efficient","title":"REBOOT: Reuse Data for Bootstrapping Efficient Real-World Dexterous Manipulation","date":"2023-09-06","arxiv_id":"2309.03322","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-neural-control-for-non-affine-control","title":"Safe Neural Control for Non-Affine Control Systems with Differentiable Control Barrier Functions","date":"2023-09-06","arxiv_id":"2309.04492","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-imitation-learning-algorithms","title":"A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges","date":"2023-09-05","arxiv_id":"2309.02473","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-driven-grounding-large-language-model","title":"Self-driven Grounding: Large Language Model Agents with Automatical Language-aligned Skill Learning","date":"2023-09-04","arxiv_id":"2309.01352","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-driving-via-self-supervised","title":"End-to-End Driving via Self-Supervised Imitation Learning Using Camera and LiDAR Data","date":"2023-08-28","arxiv_id":"2308.14329","repositories_listed":0,"syntology":null},{"url":null,"slug":"conditional-kernel-imitation-learning-for","title":"Conditional Kernel Imitation Learning for Continuous State Environments","date":"2023-08-24","arxiv_id":"2308.12573","repositories_listed":0,"syntology":null},{"url":null,"slug":"mimicking-to-dominate-imitation-learning","title":"Mimicking To Dominate: Imitation Learning Strategies for Success in Multiagent Competitive Games","date":"2023-08-20","arxiv_id":"2308.10188","repositories_listed":0,"syntology":null},{"url":null,"slug":"ilcas-imitation-learning-based-configuration","title":"ILCAS: Imitation Learning-Based Configuration-Adaptive Streaming for Live Video Analytics with Cross-Camera Collaboration","date":"2023-08-19","arxiv_id":"2308.10068","repositories_listed":0,"syntology":null},{"url":null,"slug":"preference-conditioned-pixel-based-ai-agent","title":"Preference-conditioned Pixel-based AI Agent For Game Testing","date":"2023-08-18","arxiv_id":"2308.09289","repositories_listed":0,"syntology":null},{"url":null,"slug":"imm-an-imitative-reinforcement-learning","title":"IMM: An Imitative Reinforcement Learning Approach with Predictive Representation Learning for Automatic Market Making","date":"2023-08-17","arxiv_id":"2308.08918","repositories_listed":0,"syntology":null},{"url":null,"slug":"regularizing-adversarial-imitation-learning","title":"Regularizing Adversarial Imitation Learning Using Causal Invariance","date":"2023-08-17","arxiv_id":"2308.09189","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-personas-for-games-with-multimodal","title":"Generating Personas for Games with Multimodal Adversarial Imitation Learning","date":"2023-08-15","arxiv_id":"2308.07598","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-symmetries-in-pick-and-place","title":"Leveraging Symmetries in Pick and Place","date":"2023-08-15","arxiv_id":"2308.07948","repositories_listed":0,"syntology":null},{"url":null,"slug":"developmental-bootstrapping-of-ais","title":"Bootstrapping Developmental AIs: From Simple Competences to Intelligent Human-Compatible AIs","date":"2023-08-08","arxiv_id":"2308.04586","repositories_listed":0,"syntology":null},{"url":null,"slug":"moma-force-visual-force-imitation-for-real","title":"MOMA-Force: Visual-Force Imitation for Real-World Mobile Manipulation","date":"2023-08-07","arxiv_id":"2308.03624","repositories_listed":0,"syntology":null},{"url":null,"slug":"initial-state-interventions-for-deconfounded","title":"Initial State Interventions for Deconfounded Imitation Learning","date":"2023-07-29","arxiv_id":"2307.15980","repositories_listed":0,"syntology":null},{"url":null,"slug":"waypoint-based-imitation-learning-for-robotic","title":"Waypoint-Based Imitation Learning for Robotic Manipulation","date":"2023-07-26","arxiv_id":"2307.14326","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-bandits-and-imitation-learning-via","title":"Contextual Bandits and Imitation Learning via Preference-Based Active Queries","date":"2023-07-24","arxiv_id":"2307.12926","repositories_listed":0,"syntology":null},{"url":null,"slug":"diverse-offline-imitation-via-fenchel-duality","title":"Offline Diversity Maximization Under Imitation Constraints","date":"2023-07-21","arxiv_id":"2307.11373","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-combining-expert-demonstrations-in","title":"On Combining Expert Demonstrations in Imitation Learning via Optimal Transport","date":"2023-07-20","arxiv_id":"2307.10810","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-stage-cable-routing-through","title":"Multi-Stage Cable Routing through Hierarchical Imitation Learning","date":"2023-07-18","arxiv_id":"2307.08927","repositories_listed":0,"syntology":null},{"url":null,"slug":"selective-sampling-and-imitation-learning-via","title":"Selective Sampling and Imitation Learning via Online Regression","date":"2023-07-11","arxiv_id":"2307.04998","repositories_listed":0,"syntology":null},{"url":null,"slug":"anyteleop-a-general-vision-based-dexterous","title":"AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation System","date":"2023-07-10","arxiv_id":"2307.04577","repositories_listed":0,"syntology":null},{"url":null,"slug":"decomposing-the-generalization-gap-in","title":"Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation","date":"2023-07-07","arxiv_id":"2307.03659","repositories_listed":0,"syntology":null},{"url":null,"slug":"spawnnet-learning-generalizable-visuomotor","title":"SpawnNet: Learning Generalizable Visuomotor Skills from Pre-trained Networks","date":"2023-07-07","arxiv_id":"2307.03567","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-contrastive-imitation-learning","title":"Policy Contrastive Imitation Learning","date":"2023-07-06","arxiv_id":"2307.02829","repositories_listed":0,"syntology":null},{"url":null,"slug":"rh20t-a-robotic-dataset-for-learning-diverse","title":"RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot","date":"2023-07-02","arxiv_id":"2307.00595","repositories_listed":0,"syntology":null},{"url":null,"slug":"robotic-manipulation-network-roman-hybrid","title":"RObotic MAnipulation Network (ROMAN) $\\unicode{x2013}$ Hybrid Hierarchical Learning for Solving Complex Sequential Tasks","date":"2023-06-30","arxiv_id":"2307.00125","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-dynamic-graph-for-overtaking","title":"Learning Dynamic Graph for Overtaking Strategy in Autonomous Driving","date":"2023-06-27","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ceil-generalized-contextual-imitation","title":"CEIL: Generalized Contextual Imitation Learning","date":"2023-06-26","arxiv_id":"2306.14534","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-imitation-in-mean-field-games","title":"On Imitation in Mean-field Games","date":"2023-06-26","arxiv_id":"2306.14799","repositories_listed":0,"syntology":null},{"url":null,"slug":"fighting-uncertainty-with-gradients-offline","title":"Fighting Uncertainty with Gradients: Offline Reinforcement Learning via Diffusion Score Matching","date":"2023-06-24","arxiv_id":"2306.14079","repositories_listed":0,"syntology":null},{"url":null,"slug":"clue-calibrated-latent-guidance-for-offline","title":"CLUE: Calibrated Latent Guidance for Offline Reinforcement Learning","date":"2023-06-23","arxiv_id":"2306.13412","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-shot-imitation-learning-via-interaction","title":"One-shot Imitation Learning via Interaction Warping","date":"2023-06-21","arxiv_id":"2306.12392","repositories_listed":0,"syntology":null},{"url":null,"slug":"semail-eliminating-distractors-in-visual","title":"SeMAIL: Eliminating Distractors in Visual Imitation via Separated Models","date":"2023-06-19","arxiv_id":"2306.10695","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-space-time-semantic-correspondences","title":"Learning Space-Time Semantic Correspondences","date":"2023-06-16","arxiv_id":"2306.10208","repositories_listed":0,"syntology":null},{"url":null,"slug":"predictive-maneuver-planning-with-deep","title":"Predictive Maneuver Planning with Deep Reinforcement Learning (PMP-DRL) for comfortable and safe autonomous driving","date":"2023-06-15","arxiv_id":"2306.09055","repositories_listed":0,"syntology":null},{"url":null,"slug":"residual-q-learning-offline-and-online-policy","title":"Residual Q-Learning: Offline and Online Policy Customization without Value","date":"2023-06-15","arxiv_id":"2306.09526","repositories_listed":0,"syntology":null},{"url":null,"slug":"unraveling-the-arc-puzzle-mimicking-human","title":"Unraveling the ARC Puzzle: Mimicking Human Solutions with Object-Centric Decision Transformer","date":"2023-06-14","arxiv_id":"2306.08204","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-in-robotic-motion","title":"Reinforcement Learning in Robotic Motion Planning by Combined Experience-based Planning and Self-Imitation Learning","date":"2023-06-11","arxiv_id":"2306.06754","repositories_listed":0,"syntology":null},{"url":null,"slug":"pear-primitive-enabled-adaptive-relabeling","title":"PEAR: Primitive enabled Adaptive Relabeling for boosting Hierarchical Reinforcement Learning","date":"2023-06-10","arxiv_id":"2306.06394","repositories_listed":0,"syntology":null},{"url":null,"slug":"pave-the-way-to-grasp-anything-transferring","title":"Transferring Foundation Models for Generalizable Robotic Manipulation","date":"2023-06-09","arxiv_id":"2306.05716","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequencematch-imitation-learning-for","title":"SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking","date":"2023-06-08","arxiv_id":"2306.05426","repositories_listed":0,"syntology":null},{"url":null,"slug":"divide-and-repair-using-options-to-improve","title":"Divide and Repair: Using Options to Improve Performance of Imitation Learning Against Adversarial Demonstrations","date":"2023-06-07","arxiv_id":"2306.04581","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-quality-in-imitation-learning","title":"Data Quality in Imitation Learning","date":"2023-06-04","arxiv_id":"2306.02437","repositories_listed":0,"syntology":null},{"url":null,"slug":"pagar-imitation-learning-with-protagonist","title":"PAGAR: Taming Reward Misalignment in Inverse Reinforcement Learning-Based Imitation Learning with Protagonist Antagonist Guided Adversarial Reward","date":"2023-06-02","arxiv_id":"2306.01731","repositories_listed":0,"syntology":null},{"url":null,"slug":"smooth-model-predictive-control-with","title":"On the Sample Complexity of Imitation Learning for Smoothed Model Predictive Control","date":"2023-06-02","arxiv_id":"2306.01914","repositories_listed":0,"syntology":null},{"url":null,"slug":"causal-imitability-under-context-specific","title":"Causal Imitability Under Context-Specific Independence Relations","date":"2023-06-01","arxiv_id":"2306.00585","repositories_listed":0,"syntology":null},{"url":null,"slug":"gan-mpc-training-model-predictive-controllers","title":"GAN-MPC: Training Model Predictive Controllers with Parameterized Cost Functions using Demonstrations from Non-identical Experts","date":"2023-05-30","arxiv_id":"2305.19111","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-conditioned-imitation-learning-with","title":"Language-Conditioned Imitation Learning with Base Skill Priors under Unstructured Data","date":"2023-05-30","arxiv_id":"2305.19075","repositories_listed":0,"syntology":null},{"url":null,"slug":"emergent-agentic-transformer-from-chain-of","title":"Emergent Agentic Transformer from Chain of Hindsight Experience","date":"2023-05-26","arxiv_id":"2305.16554","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-to-not-train-your-dragon-training-free","title":"How To Not Train Your Dragon: Training-free Embodied Object Goal Navigation with Semantic Frontiers","date":"2023-05-26","arxiv_id":"2305.16925","repositories_listed":0,"syntology":null},{"url":null,"slug":"asking-before-action-gather-information-in","title":"Asking Before Acting: Gather Information in Embodied Decision Making with Language Models","date":"2023-05-25","arxiv_id":"2305.15695","repositories_listed":0,"syntology":null}],"record_sha256":"e4c4c51e079f9dbff8e158c3e2f9c14963b722461f4daf811969fc061df4e3fe","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}