{"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/15","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":15,"pages_in_order":22,"rows_per_page":100,"rows":[1401,1500],"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/14","next":"/task/imitation-learning/papers/16","papers":[{"url":null,"slug":"learning-from-demonstrations-of-critical","title":"Learning from Demonstrations of Critical Driving Behaviours Using Driver's Risk Field","date":"2022-10-04","arxiv_id":"2210.01747","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-perception-aware-agile-flight-in","title":"Learning Perception-Aware Agile Flight in Cluttered Environments","date":"2022-10-04","arxiv_id":"2210.01841","repositories_listed":0,"syntology":null},{"url":null,"slug":"maximum-likelihood-inverse-reinforcement","title":"Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees","date":"2022-10-04","arxiv_id":"2210.01808","repositories_listed":0,"syntology":null},{"url":null,"slug":"structural-estimation-of-markov-decision","title":"Structural Estimation of Markov Decision Processes in High-Dimensional State Space with Finite-Time Guarantees","date":"2022-10-04","arxiv_id":"2210.01282","repositories_listed":0,"syntology":null},{"url":null,"slug":"dissipative-imitation-learning-for-robust","title":"Dissipative Imitation Learning for Robust Dynamic Output Feedback","date":"2022-10-03","arxiv_id":"2210.00979","repositories_listed":0,"syntology":null},{"url":null,"slug":"regularized-soft-actor-critic-for-behavior","title":"Regularized Soft Actor-Critic for Behavior Transfer Learning","date":"2022-09-27","arxiv_id":"2209.13224","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-efficient-online-imitation-learning-via","title":"On Efficient Online Imitation Learning via Classification","date":"2022-09-26","arxiv_id":"2209.12868","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-hindsight-goal-relabeling","title":"Understanding Hindsight Goal Relabeling from a Divergence Minimization Perspective","date":"2022-09-26","arxiv_id":"2209.13046","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-neural-networks-for-multi-robot-active","title":"Graph Neural Networks for Multi-Robot Active Information Acquisition","date":"2022-09-24","arxiv_id":"2209.12091","repositories_listed":0,"syntology":null},{"url":null,"slug":"learn-what-matters-cross-domain-imitation","title":"Learn what matters: cross-domain imitation learning with task-relevant embeddings","date":"2022-09-24","arxiv_id":"2209.12093","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-model-predictive-controllers-with","title":"Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigation","date":"2022-09-22","arxiv_id":"2209.10780","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-crop-management-with-reinforcement","title":"Optimizing Crop Management with Reinforcement Learning and Imitation Learning","date":"2022-09-20","arxiv_id":"2209.09991","repositories_listed":0,"syntology":null},{"url":null,"slug":"gesture2path-imitation-learning-for-gesture","title":"Gesture2Path: Imitation Learning for Gesture-aware Navigation","date":"2022-09-19","arxiv_id":"2209.09375","repositories_listed":0,"syntology":null},{"url":null,"slug":"msviper-improved-policy-distillation-for","title":"MSVIPER: Improved Policy Distillation for Reinforcement-Learning-Based Robot Navigation","date":"2022-09-19","arxiv_id":"2209.09079","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial-temporal-deep-embedding-for-vehicle","title":"Spatial-Temporal Deep Embedding for Vehicle Trajectory Reconstruction from High-Angle Video","date":"2022-09-17","arxiv_id":"2209.08417","repositories_listed":0,"syntology":null},{"url":null,"slug":"centerlinedet-road-lane-centerline-graph","title":"CenterLineDet: CenterLine Graph Detection for Road Lanes with Vehicle-mounted Sensors by Transformer for HD Map Generation","date":"2022-09-16","arxiv_id":"2209.07734","repositories_listed":0,"syntology":null},{"url":null,"slug":"masked-imitation-learning-discovering","title":"Masked Imitation Learning: Discovering Environment-Invariant Modalities in Multimodal Demonstrations","date":"2022-09-16","arxiv_id":"2209.07682","repositories_listed":0,"syntology":null},{"url":null,"slug":"versatile-skill-control-via-self-supervised","title":"Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions","date":"2022-09-16","arxiv_id":"2209.07899","repositories_listed":0,"syntology":null},{"url":null,"slug":"handmime-sign-language-fingerspelling","title":"Signs of Language: Embodied Sign Language Fingerspelling Acquisition from Demonstrations for Human-Robot Interaction","date":"2022-09-12","arxiv_id":"2209.05135","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-memory-related-multi-task-method-based-on","title":"Task-Agnostic Learning to Accomplish New Tasks","date":"2022-09-09","arxiv_id":"2209.04100","repositories_listed":0,"syntology":null},{"url":null,"slug":"co-imitation-learning-design-and-behaviour-by","title":"Co-Imitation: Learning Design and Behaviour by Imitation","date":"2022-09-02","arxiv_id":"2209.01207","repositories_listed":0,"syntology":null},{"url":null,"slug":"targf-learning-target-gradient-field-for","title":"TarGF: Learning Target Gradient Field to Rearrange Objects without Explicit Goal Specification","date":"2022-09-02","arxiv_id":"2209.00853","repositories_listed":0,"syntology":null},{"url":null,"slug":"metatrader-an-reinforcement-learning-approach","title":"MetaTrader: An Reinforcement Learning Approach Integrating Diverse Policies for Portfolio Optimization","date":"2022-09-01","arxiv_id":"2210.01774","repositories_listed":0,"syntology":null},{"url":null,"slug":"weighted-maximum-entropy-inverse","title":"Weighted Maximum Entropy Inverse Reinforcement Learning","date":"2022-08-20","arxiv_id":"2208.09611","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-structure-an-image-with-few-1","title":"Learning to Structure an Image with Few Colors and Beyond","date":"2022-08-17","arxiv_id":"2208.08438","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-informed-design-and-validation","title":"Towards Informed Design and Validation Assistance in Computer Games Using Imitation Learning","date":"2022-08-15","arxiv_id":"2208.07811","repositories_listed":0,"syntology":null},{"url":null,"slug":"causal-imitation-learning-with-unobserved-1","title":"Causal Imitation Learning with Unobserved Confounders","date":"2022-08-12","arxiv_id":"2208.06267","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequential-causal-imitation-learning-with-1","title":"Sequential Causal Imitation Learning with Unobserved Confounders","date":"2022-08-12","arxiv_id":"2208.06276","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-trade-off-between-human-driving","title":"Exploring the trade off between human driving imitation and safety for traffic simulation","date":"2022-08-09","arxiv_id":"2208.04803","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-adversarial-imitation-learning","title":"Understanding Adversarial Imitation Learning in Small Sample Regime: A Stage-coupled Analysis","date":"2022-08-03","arxiv_id":"2208.01899","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-navigate-using-visual-sensor","title":"See What the Robot Can't See: Learning Cooperative Perception for Visual Navigation","date":"2022-08-01","arxiv_id":"2208.00759","repositories_listed":0,"syntology":null},{"url":null,"slug":"robot-policy-learning-from-demonstration","title":"Robot Policy Learning from Demonstration Using Advantage Weighting and Early Termination","date":"2022-07-31","arxiv_id":"2208.00478","repositories_listed":0,"syntology":null},{"url":null,"slug":"robots-enact-malignant-stereotypes","title":"Robots Enact Malignant Stereotypes","date":"2022-07-23","arxiv_id":"2207.11569","repositories_listed":0,"syntology":null},{"url":null,"slug":"lagrangian-method-for-q-function-learning","title":"Lagrangian Method for Q-Function Learning (with Applications to Machine Translation)","date":"2022-07-22","arxiv_id":"2207.11161","repositories_listed":0,"syntology":null},{"url":null,"slug":"resolving-copycat-problems-in-visual","title":"Resolving Copycat Problems in Visual Imitation Learning via Residual Action Prediction","date":"2022-07-20","arxiv_id":"2207.09705","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-few-expert-queries-suffices-for-sample","title":"A Few Expert Queries Suffices for Sample-Efficient RL with Resets and Linear Value Approximation","date":"2022-07-18","arxiv_id":"2207.08342","repositories_listed":0,"syntology":null},{"url":null,"slug":"inspector-pixel-based-automated-game-testing","title":"Inspector: Pixel-Based Automated Game Testing via Exploration, Detection, and Investigation","date":"2022-07-18","arxiv_id":"2207.08379","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-prove-trigonometric-identities","title":"Learning to Prove Trigonometric Identities","date":"2022-07-14","arxiv_id":"2207.06679","repositories_listed":0,"syntology":null},{"url":null,"slug":"finding-fallen-objects-via-asynchronous-audio-1","title":"Finding Fallen Objects Via Asynchronous Audio-Visual Integration","date":"2022-07-07","arxiv_id":"2207.03483","repositories_listed":0,"syntology":null},{"url":null,"slug":"planning-with-rl-and-episodic-memory","title":"Planning with RL and episodic-memory behavioral priors","date":"2022-07-05","arxiv_id":"2207.01845","repositories_listed":0,"syntology":null},{"url":null,"slug":"discriminator-guided-model-based-offline","title":"Discriminator-Guided Model-Based Offline Imitation Learning","date":"2022-07-01","arxiv_id":"2207.00244","repositories_listed":0,"syntology":null},{"url":null,"slug":"watch-and-match-supercharging-imitation-with","title":"Watch and Match: Supercharging Imitation with Regularized Optimal Transport","date":"2022-06-30","arxiv_id":"2206.15469","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-energy-efficient-driving-behaviors","title":"Learning energy-efficient driving behaviors by imitating experts","date":"2022-06-28","arxiv_id":"2208.12534","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-cut-by-looking-ahead-cutting","title":"Learning To Cut By Looking Ahead: Cutting Plane Selection via Imitation Learning","date":"2022-06-27","arxiv_id":"2206.13414","repositories_listed":0,"syntology":null},{"url":null,"slug":"auto-encoding-adversarial-imitation-learning","title":"Auto-Encoding Adversarial Imitation Learning","date":"2022-06-22","arxiv_id":"2206.11004","repositories_listed":0,"syntology":null},{"url":null,"slug":"fighting-fire-with-fire-avoiding-dnn","title":"Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming","date":"2022-06-22","arxiv_id":"2206.10816","repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-policies-for-adversarial-imitation","title":"Latent Policies for Adversarial Imitation Learning","date":"2022-06-22","arxiv_id":"2206.11299","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitate-then-transcend-multi-agent-optimal","title":"Imitate then Transcend: Multi-Agent Optimal Execution with Dual-Window Denoise PPO","date":"2022-06-21","arxiv_id":"2206.10736","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-based-imitation-learning-using-entropy","title":"Model-Based Imitation Learning Using Entropy Regularization of Model and Policy","date":"2022-06-21","arxiv_id":"2206.10101","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-multi-task-transferable-rewards-via","title":"Learning Multi-Task Transferable Rewards via Variational Inverse Reinforcement Learning","date":"2022-06-19","arxiv_id":"2206.09498","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-exact","title":"Deep Reinforcement Learning for Exact Combinatorial Optimization: Learning to Branch","date":"2022-06-14","arxiv_id":"2206.06965","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-based-offline-imitation-learning-with","title":"Model-based Offline Imitation Learning with Non-expert Data","date":"2022-06-11","arxiv_id":"2206.05521","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-solutions-for-joint-beamforming-and","title":"Optimal Solutions for Joint Beamforming and Antenna Selection: From Branch and Bound to Graph Neural Imitation Learning","date":"2022-06-11","arxiv_id":"2206.05576","repositories_listed":0,"syntology":null},{"url":null,"slug":"precise-affordance-annotation-for-egocentric","title":"Precise Affordance Annotation for Egocentric Action Video Datasets","date":"2022-06-11","arxiv_id":"2206.05424","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-logic-imitation-learning-plan","title":"Temporal Logic Imitation: Learning Plan-Satisficing Motion Policies from Demonstrations","date":"2022-06-09","arxiv_id":"2206.04632","repositories_listed":0,"syntology":null},{"url":null,"slug":"driving-in-real-life-with-inverse","title":"Driving in Real Life with Inverse Reinforcement Learning","date":"2022-06-07","arxiv_id":"2206.03004","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitating-past-successes-can-be-very","title":"Imitating Past Successes can be Very Suboptimal","date":"2022-06-07","arxiv_id":"2206.03378","repositories_listed":0,"syntology":null},{"url":null,"slug":"arc-actor-residual-critic-for-adversarial","title":"ARC -- Actor Residual Critic for Adversarial Imitation Learning","date":"2022-06-05","arxiv_id":"2206.02095","repositories_listed":0,"syntology":null},{"url":null,"slug":"transferable-reward-learning-by-dynamics","title":"Transferable Reward Learning by Dynamics-Agnostic Discriminator Ensemble","date":"2022-06-01","arxiv_id":"2206.00238","repositories_listed":0,"syntology":null},{"url":null,"slug":"play-it-by-ear-learning-skills-amidst","title":"Play it by Ear: Learning Skills amidst Occlusion through Audio-Visual Imitation Learning","date":"2022-05-30","arxiv_id":"2205.14850","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-augmentation-for-efficient-learning-from-1","title":"Data augmentation for efficient learning from parametric experts","date":"2022-05-23","arxiv_id":"2205.11448","repositories_listed":0,"syntology":null},{"url":null,"slug":"il-flow-imitation-learning-from-observation","title":"IL-flOw: Imitation Learning from Observation using Normalizing Flows","date":"2022-05-19","arxiv_id":"2205.09251","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-energy-networks-with-generalized","title":"Learning Energy Networks with Generalized Fenchel-Young Losses","date":"2022-05-19","arxiv_id":"2205.09589","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalizing-to-new-tasks-via-one-shot","title":"Generalizing to New Tasks via One-Shot Compositional Subgoals","date":"2022-05-16","arxiv_id":"2205.07716","repositories_listed":0,"syntology":null},{"url":null,"slug":"delayed-reinforcement-learning-by-imitation","title":"Delayed Reinforcement Learning by Imitation","date":"2022-05-11","arxiv_id":"2205.05569","repositories_listed":0,"syntology":null},{"url":null,"slug":"risp-rendering-invariant-state-predictor-with-1","title":"RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimation","date":"2022-05-11","arxiv_id":"2205.05678","repositories_listed":0,"syntology":null},{"url":null,"slug":"diverse-imitation-learning-via-self-1","title":"Diverse Imitation Learning via Self-Organizing Generative Models","date":"2022-05-06","arxiv_id":"2205.03484","repositories_listed":0,"syntology":null},{"url":null,"slug":"issues-in-cross-domain-imitation-learning-via","title":"Hitting time for Markov decision process","date":"2022-05-06","arxiv_id":"2205.03476","repositories_listed":0,"syntology":null},{"url":null,"slug":"skill-il-disentangling-skill-and-knowledge-in","title":"SKILL-IL: Disentangling Skill and Knowledge in Multitask Imitation Learning","date":"2022-05-06","arxiv_id":"2205.03130","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-makes-a-good-fisherman-linear-regression","title":"What Makes A Good Fisherman? Linear Regression under Self-Selection Bias","date":"2022-05-06","arxiv_id":"2205.03246","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-imitation-learning-of-team","title":"Semi-Supervised Imitation Learning of Team Policies from Suboptimal Demonstrations","date":"2022-05-05","arxiv_id":"2205.02959","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-one-hand-to-multiple-hands-imitation","title":"From One Hand to Multiple Hands: Imitation Learning for Dexterous Manipulation from Single-Camera Teleoperation","date":"2022-04-26","arxiv_id":"2204.12490","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-value-functions-from-undirected-1","title":"Learning Value Functions from Undirected State-only Experience","date":"2022-04-26","arxiv_id":"2204.12458","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-induced-representation-learning-1","title":"Task-Induced Representation Learning","date":"2022-04-25","arxiv_id":"2204.11827","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-fold-real-garments-with-one-arm-a","title":"Learning to Fold Real Garments with One Arm: A Case Study in Cloud-Based Robotics Research","date":"2022-04-21","arxiv_id":"2204.10297","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-of-causal-confusion-in-preference","title":"Causal Confusion and Reward Misidentification in Preference-Based Reward Learning","date":"2022-04-13","arxiv_id":"2204.06601","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-should-we-prefer-offline-reinforcement","title":"When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?","date":"2022-04-12","arxiv_id":"2204.05618","repositories_listed":0,"syntology":null},{"url":null,"slug":"habitat-web-learning-embodied-object-search","title":"Habitat-Web: Learning Embodied Object-Search Strategies from Human Demonstrations at Scale","date":"2022-04-07","arxiv_id":"2204.03514","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitating-fast-and-slow-robust-learning-from","title":"Imitating, Fast and Slow: Robust learning from demonstrations via decision-time planning","date":"2022-04-07","arxiv_id":"2204.03597","repositories_listed":0,"syntology":null},{"url":null,"slug":"demonstrate-once-imitate-immediately-dome","title":"Demonstrate Once, Imitate Immediately (DOME): Learning Visual Servoing for One-Shot Imitation Learning","date":"2022-04-06","arxiv_id":"2204.02863","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-generalizable-dexterous-manipulation","title":"Learning Generalizable Dexterous Manipulation from Human Grasp Affordance","date":"2022-04-05","arxiv_id":"2204.02320","repositories_listed":0,"syntology":null},{"url":null,"slug":"information-theoretic-policy-extraction-from","title":"Information-Theoretic Policy Learning from Partial Observations with Fully Informed Decision Makers","date":"2022-04-04","arxiv_id":"2204.02350","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-federated-edge-learning-via-1","title":"Accelerating Federated Edge Learning via Topology Optimization","date":"2022-04-01","arxiv_id":"2204.00489","repositories_listed":0,"syntology":null},{"url":null,"slug":"reil-a-framework-for-reinforced-intervention","title":"ReIL: A Framework for Reinforced Intervention-based Imitation Learning","date":"2022-03-29","arxiv_id":"2203.15390","repositories_listed":0,"syntology":null},{"url":"/paper/socially-compliant-navigation-dataset-scand-a","slug":"socially-compliant-navigation-dataset-scand-a","title":"Socially Compliant Navigation Dataset (SCAND): A Large-Scale Dataset of Demonstrations for Social Navigation","date":"2022-03-28","arxiv_id":"2203.15041","repositories_listed":0,"syntology":null},{"url":null,"slug":"reshaping-robot-trajectories-using-natural","title":"Reshaping Robot Trajectories Using Natural Language Commands: A Study of Multi-Modal Data Alignment Using Transformers","date":"2022-03-25","arxiv_id":"2203.13411","repositories_listed":0,"syntology":null},{"url":null,"slug":"dexterous-imitation-made-easy-a-learning","title":"Dexterous Imitation Made Easy: A Learning-Based Framework for Efficient Dexterous Manipulation","date":"2022-03-24","arxiv_id":"2203.13251","repositories_listed":0,"syntology":null},{"url":null,"slug":"advanced-skills-through-multiple-adversarial","title":"Advanced Skills through Multiple Adversarial Motion Priors in Reinforcement Learning","date":"2022-03-23","arxiv_id":"2203.14912","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-imitation-learning-from-demonstrations","title":"Self-Imitation Learning from Demonstrations","date":"2022-03-21","arxiv_id":"2203.10905","repositories_listed":0,"syntology":null},{"url":null,"slug":"robot-peels-banana-with-goal-conditioned-dual","title":"Goal-conditioned dual-action imitation learning for dexterous dual-arm robot manipulation","date":"2022-03-18","arxiv_id":"2203.09749","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-imitation-learning-curriculum-for-text","title":"An Imitation Learning Curriculum for Text Editing with Non-Autoregressive Models","date":"2022-03-17","arxiv_id":"2203.09486","repositories_listed":0,"syntology":null},{"url":null,"slug":"causal-robot-communication-inspired-by","title":"Causal Robot Communication Inspired by Observational Learning Insights","date":"2022-03-17","arxiv_id":"2203.09114","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-architectures-for-compositional","title":"Policy Architectures for Compositional Generalization in Control","date":"2022-03-10","arxiv_id":"2203.05960","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-sensorimotor-primitives-of","title":"Learning Sensorimotor Primitives of Sequential Manipulation Tasks from Visual Demonstrations","date":"2022-03-08","arxiv_id":"2203.03797","repositories_listed":0,"syntology":null},{"url":null,"slug":"find-a-way-forward-a-language-guided-semantic","title":"Find a Way Forward: a Language-Guided Semantic Map Navigator","date":"2022-03-07","arxiv_id":"2203.03183","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-solution-manifolds-for-control","title":"Learning Solution Manifolds for Control Problems via Energy Minimization","date":"2022-03-07","arxiv_id":"2203.03432","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-adaptive-human-driver-model-for-realistic","title":"An Adaptive Human Driver Model for Realistic Race Car Simulations","date":"2022-03-03","arxiv_id":"2203.01909","repositories_listed":0,"syntology":null},{"url":null,"slug":"firl-fast-imitation-and-policy-reuse-learning","title":"A Versatile Agent for Fast Learning from Human Instructors","date":"2022-03-01","arxiv_id":"2203.00251","repositories_listed":0,"syntology":null},{"url":null,"slug":"transporters-with-visual-foresight-for","title":"Transporters with Visual Foresight for Solving Unseen Rearrangement Tasks","date":"2022-02-22","arxiv_id":"2202.10765","repositories_listed":0,"syntology":null},{"url":null,"slug":"ccpt-automatic-gameplay-testing-and","title":"CCPT: Automatic Gameplay Testing and Validation with Curiosity-Conditioned Proximal Trajectories","date":"2022-02-21","arxiv_id":"2202.10057","repositories_listed":0,"syntology":null}],"record_sha256":"b2a7db44fe99792489f0700aa39ff0e57633964c629a7c659b1e9ac350a91df1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}