{"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/16","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":16,"pages_in_order":22,"rows_per_page":100,"rows":[1501,1600],"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/15","next":"/task/imitation-learning/papers/17","papers":[{"url":null,"slug":"multi-task-conditional-imitation-learning-for","title":"Multi-Task Conditional Imitation Learning for Autonomous Navigation at Crowded Intersections","date":"2022-02-21","arxiv_id":"2202.10124","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-robots-without-robots-deep-imitation","title":"Training Robots without Robots: Deep Imitation Learning for Master-to-Robot Policy Transfer","date":"2022-02-19","arxiv_id":"2202.09574","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-learning-of-safe-driving-policy-via-1","title":"Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization","date":"2022-02-17","arxiv_id":"2202.10341","repositories_listed":0,"syntology":null},{"url":null,"slug":"rngdet-road-network-graph-detection-by","title":"RNGDet: Road Network Graph Detection by Transformer in Aerial Images","date":"2022-02-16","arxiv_id":"2202.07824","repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-imitation-learning-for-end-to-end","title":"Bayesian Imitation Learning for End-to-End Mobile Manipulation","date":"2022-02-15","arxiv_id":"2202.07600","repositories_listed":0,"syntology":null},{"url":null,"slug":"robots-learn-increasingly-complex-tasks-with","title":"Robots Learn Increasingly Complex Tasks with Intrinsic Motivation and Automatic Curriculum Learning","date":"2022-02-11","arxiv_id":"2202.10222","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-based-gaze-prediction-in-deep","title":"Memory-based gaze prediction in deep imitation learning for robot manipulation","date":"2022-02-10","arxiv_id":"2202.04877","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-ranking-game-for-imitation-learning","title":"A Ranking Game for Imitation Learning","date":"2022-02-07","arxiv_id":"2202.03481","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-valuedice-does-it-really-improve","title":"Rethinking ValueDice: Does It Really Improve Performance?","date":"2022-02-05","arxiv_id":"2202.02468","repositories_listed":0,"syntology":null},{"url":null,"slug":"bc-z-zero-shot-task-generalization-with","title":"BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning","date":"2022-02-04","arxiv_id":"2202.02005","repositories_listed":0,"syntology":null},{"url":null,"slug":"challenging-common-assumptions-in-convex","title":"Challenging Common Assumptions in Convex Reinforcement Learning","date":"2022-02-03","arxiv_id":"2202.01511","repositories_listed":0,"syntology":null},{"url":null,"slug":"practical-imitation-learning-in-the-real","title":"Practical Imitation Learning in the Real World via Task Consistency Loss","date":"2022-02-03","arxiv_id":"2202.01862","repositories_listed":0,"syntology":null},{"url":null,"slug":"yordle-an-efficient-imitation-learning-for","title":"Yordle: An Efficient Imitation Learning for Branch and Bound","date":"2022-02-02","arxiv_id":"2202.01896","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-imitation-learning-from-video","title":"Adversarial Imitation Learning from Video using a State Observer","date":"2022-02-01","arxiv_id":"2202.00243","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-imitation-learning-from-corrupted-1","title":"Robust Imitation Learning from Corrupted Demonstrations","date":"2022-01-29","arxiv_id":"2201.12594","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfering-hierarchical-structure-with-dual","title":"Transfering Hierarchical Structure with Dual Meta Imitation Learning","date":"2022-01-28","arxiv_id":"2201.11981","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-routing-on-proximity-graph-for","title":"Reinforcement Routing on Proximity Graph for Efficient Recommendation","date":"2022-01-23","arxiv_id":"2201.09290","repositories_listed":0,"syntology":null},{"url":null,"slug":"ray-based-distributed-autonomous-vehicle","title":"Ray Based Distributed Autonomous Vehicle Research Platform","date":"2022-01-18","arxiv_id":"2201.06835","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-improved-reinforcement-learning-algorithm","title":"An Improved Reinforcement Learning Algorithm for Learning to Branch","date":"2022-01-17","arxiv_id":"2201.06213","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-valuedice-does-it-really-improve-1","title":"Rethinking ValueDice: Does It Really Improve Performance?","date":"2022-01-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"profitable-strategy-design-by-using-deep","title":"Profitable Strategy Design by Using Deep Reinforcement Learning for Trades on Cryptocurrency Markets","date":"2022-01-15","arxiv_id":"2201.05906","repositories_listed":0,"syntology":null},{"url":null,"slug":"reward-relabelling-for-combined-reinforcement","title":"STIR$^2$: Reward Relabelling for combined Reinforcement and Imitation Learning on sparse-reward tasks","date":"2022-01-11","arxiv_id":"2201.03834","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-attention-prediction-improves","title":"Visual Attention Prediction Improves Performance of Autonomous Drone Racing Agents","date":"2022-01-07","arxiv_id":"2201.02569","repositories_listed":0,"syntology":null},{"url":null,"slug":"conditional-imitation-learning-for-multi","title":"Conditional Imitation Learning for Multi-Agent Games","date":"2022-01-05","arxiv_id":"2201.01448","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-entropy-regularized-markov-decision","title":"Robust Entropy-regularized Markov Decision Processes","date":"2021-12-31","arxiv_id":"2112.15364","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-convex-optimization-for-provably","title":"Stochastic convex optimization for provably efficient apprenticeship learning","date":"2021-12-31","arxiv_id":"2201.00039","repositories_listed":0,"syntology":null},{"url":null,"slug":"parallelized-and-randomized-adversarial","title":"Parallelized and Randomized Adversarial Imitation Learning for Safety-Critical Self-Driving Vehicles","date":"2021-12-26","arxiv_id":"2112.14710","repositories_listed":0,"syntology":null},{"url":null,"slug":"amortized-noisy-channel-neural-machine","title":"Amortized Noisy Channel Neural Machine Translation","date":"2021-12-16","arxiv_id":"2112.08670","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-strong-and-human-like-gameplay-with","title":"Modeling Strong and Human-Like Gameplay with KL-Regularized Search","date":"2021-12-14","arxiv_id":"2112.07544","repositories_listed":0,"syntology":null},{"url":null,"slug":"probability-density-estimation-based","title":"Probability Density Estimation Based Imitation Learning","date":"2021-12-13","arxiv_id":"2112.06746","repositories_listed":0,"syntology":null},{"url":null,"slug":"error-aware-imitation-learning-from","title":"Error-Aware Imitation Learning from Teleoperation Data for Mobile Manipulation","date":"2021-12-09","arxiv_id":"2112.05251","repositories_listed":0,"syntology":null},{"url":null,"slug":"creating-multimodal-interactive-agents-with","title":"Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning","date":"2021-12-07","arxiv_id":"2112.03763","repositories_listed":0,"syntology":null},{"url":null,"slug":"juewu-mc-playing-minecraft-with-sample","title":"JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning","date":"2021-12-07","arxiv_id":"2112.04907","repositories_listed":0,"syntology":null},{"url":null,"slug":"guided-imitation-of-task-and-motion-planning","title":"Guided Imitation of Task and Motion Planning","date":"2021-12-06","arxiv_id":"2112.03386","repositories_listed":0,"syntology":null},{"url":null,"slug":"mdpfuzzer-finding-crash-triggering-state","title":"MDPFuzz: Testing Models Solving Markov Decision Processes","date":"2021-12-06","arxiv_id":"2112.02807","repositories_listed":0,"syntology":null},{"url":null,"slug":"organ-localisation-using-supervised-and-semi","title":"Organ localisation using supervised and semi supervised approaches combining reinforcement learning with imitation learning","date":"2021-12-06","arxiv_id":"2112.03276","repositories_listed":0,"syntology":null},{"url":null,"slug":"stage-conscious-attention-network-scan-a","title":"Stage Conscious Attention Network (SCAN) : A Demonstration-Conditioned Policy for Few-Shot Imitation","date":"2021-12-04","arxiv_id":"2112.02278","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantile-filtered-imitation-learning","title":"Quantile Filtered Imitation Learning","date":"2021-12-02","arxiv_id":"2112.00950","repositories_listed":0,"syntology":null},{"url":null,"slug":"curriculum-offline-imitating-learning","title":"Curriculum Offline Imitating Learning","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"distributionally-robust-imitation-learning","title":"Distributionally Robust Imitation Learning","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"document-level-hierarchical-transformer","title":"Document Level Hierarchical Transformer","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generalizable-imitation-learning-from","title":"Generalizable Imitation Learning from Observation via Inferring Goal Proximity","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-value-of-interaction-and-function","title":"On the Value of Interaction and Function Approximation in Imitation Learning","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-inference","title":"Dynamic Inference","date":"2021-11-29","arxiv_id":"2111.14746","repositories_listed":0,"syntology":null},{"url":null,"slug":"back-to-reality-for-imitation-learning","title":"Back to Reality for Imitation Learning","date":"2021-11-25","arxiv_id":"2111.12867","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-column-generation-for-capacitated","title":"Neural Column Generation for Capacitated Vehicle Routing","date":"2021-11-24","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sample-efficient-imitation-learning-via-1","title":"Sample Efficient Imitation Learning via Reward Function Trained in Advance","date":"2021-11-23","arxiv_id":"2111.11711","repositories_listed":0,"syntology":null},{"url":null,"slug":"nnsynth-neural-network-guided-abstraction","title":"NNSynth: Neural Network Guided Abstraction-Based Controller Synthesis for Stochastic Systems","date":"2021-11-17","arxiv_id":"2111.08853","repositories_listed":0,"syntology":null},{"url":null,"slug":"seihai-a-sample-efficient-hierarchical-ai-for","title":"SEIHAI: A Sample-efficient Hierarchical AI for the MineRL Competition","date":"2021-11-17","arxiv_id":"2111.08857","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-learning-from-demonstrations-by-1","title":"Improving Learning from Demonstrations by Learning from Experience","date":"2021-11-16","arxiv_id":"2111.08156","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-multi-stage-tasks-with-one","title":"Learning Multi-Stage Tasks with One Demonstration via Self-Replay","date":"2021-11-14","arxiv_id":"2111.07447","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-based-reinforcement-learning-for-5","title":"Model-Based Reinforcement Learning via Stochastic Hybrid Models","date":"2021-11-11","arxiv_id":"2111.06211","repositories_listed":0,"syntology":null},{"url":null,"slug":"off-policy-imitation-learning-from-visual","title":"Off-policy Imitation Learning from Visual Inputs","date":"2021-11-08","arxiv_id":"2111.04345","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-bang-bang-control-all-you-need-solving","title":"Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies","date":"2021-11-03","arxiv_id":"2111.02552","repositories_listed":0,"syntology":null},{"url":null,"slug":"smooth-imitation-learning-via-smooth-costs","title":"Smooth Imitation Learning via Smooth Costs and Smooth Policies","date":"2021-11-03","arxiv_id":"2111.02354","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-robotic-ultrasound-scanning-skills","title":"Learning Robotic Ultrasound Scanning Skills via Human Demonstrations and Guided Explorations","date":"2021-11-02","arxiv_id":"2111.01625","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-coordinated-terrain-adaptive","title":"Learning Coordinated Terrain-Adaptive Locomotion by Imitating a Centroidal Dynamics Planner","date":"2021-10-30","arxiv_id":"2111.00262","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-more-generalizable-one-shot-visual","title":"Towards More Generalizable One-shot Visual Imitation Learning","date":"2021-10-26","arxiv_id":"2110.13423","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-robotic-manipulation-through","title":"Efficient Robotic Manipulation Through Offline-to-Online Reinforcement Learning and Goal-Aware State Information","date":"2021-10-21","arxiv_id":"2110.10905","repositories_listed":0,"syntology":null},{"url":null,"slug":"periodic-dmp-formulation-for-quaternion","title":"Periodic DMP formulation for Quaternion Trajectories","date":"2021-10-20","arxiv_id":"2110.10510","repositories_listed":0,"syntology":null},{"url":null,"slug":"ss-mail-self-supervised-multi-agent-imitation-1","title":"SS-MAIL: Self-Supervised Multi-Agent Imitation Learning","date":"2021-10-18","arxiv_id":"2110.08963","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-adversarial-imitation-learning-for-1","title":"Generative Adversarial Imitation Learning for End-to-End Autonomous Driving on Urban Environments","date":"2021-10-16","arxiv_id":"2110.08586","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-covariate-shift-of-latent-confounders-in-1","title":"On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning","date":"2021-10-13","arxiv_id":"2110.06539","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-experience-in-lazy-search-1","title":"Leveraging Experience in Lazy Search","date":"2021-10-10","arxiv_id":"2110.04669","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-imitation-learning-on-real-life-highway","title":"Safe Imitation Learning on Real-Life Highway Data for Human-like Autonomous Driving","date":"2021-10-08","arxiv_id":"2110.04052","repositories_listed":0,"syntology":null},{"url":null,"slug":"goal-directed-design-agents-integrating","title":"Goal-Directed Design Agents: Integrating Visual Imitation with One-Step Lookahead Optimization for Generative Design","date":"2021-10-07","arxiv_id":"2110.03223","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-critique-of-strictly-batch-imitation","title":"A Critique of Strictly Batch Imitation Learning","date":"2021-10-05","arxiv_id":"2110.02063","repositories_listed":0,"syntology":null},{"url":null,"slug":"procedure-planning-in-instructional-videosvia","title":"Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learning","date":"2021-10-05","arxiv_id":"2110.01770","repositories_listed":0,"syntology":null},{"url":null,"slug":"auto-encoding-inverse-reinforcement-learning","title":"Auto-Encoding Inverse Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-sample-selection-strategies-for","title":"Benchmarking Sample Selection Strategies for Batch Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"crowdplay-crowdsourcing-human-demonstration","title":"CrowdPlay: Crowdsourcing human demonstration data for offline learning in Atari games","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"demodice-offline-imitation-learning-with","title":"DemoDICE: Offline Imitation Learning with Supplementary Imperfect Demonstrations","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"distributional-decision-transformer-for","title":"Distributional Decision Transformer for Hindsight Information Matching","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"diverse-imitation-learning-via-self","title":"Diverse Imitation Learning via Self-OrganizingGenerative Models","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-fixed-backbone-protein-sequence-and","title":"Fast fixed-backbone protein sequence and rotamer design","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fight-fire-with-fire-countering-bad-shortcuts","title":"Fight fire with fire: countering bad shortcuts in imitation learning with good shortcuts","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-learning-from-pixel-observations","title":"Imitation Learning from Pixel Observations for Continuous Control","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lagrangian-generative-adversarial-imitation","title":"Lagrangian Generative Adversarial Imitation Learning with Safety","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lagrangian-method-for-episodic-learning","title":"Lagrangian Method for Episodic Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-pre-training-improves","title":"Language Model Pre-training Improves Generalization in Policy Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-the-representation-of-behavior","title":"Learning the Representation of Behavior Styles with Imitation Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-imitation-learning-by-watching-video","title":"Meta-Imitation Learning by Watching Video Demonstrations","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigation-of-adversarial-policy-imitation","title":"Mitigation of Adversarial Policy Imitation via Constrained Randomization of Policy (CRoP)","date":"2021-09-29","arxiv_id":"2109.14678","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-batch-reinforcement-learning-via-sample","title":"Multi-batch Reinforcement Learning via Sample Transfer and Imitation Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"plan-your-target-and-learn-your-skills-state","title":"Plan Your Target and Learn Your Skills: State-Only Imitation Learning via Decoupled Policy Optimization","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"stabilized-likelihood-based-imitation","title":"Stabilized Likelihood-based Imitation Learning via Denoising Continuous Normalizing Flow","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"state-only-imitation-learning-by-trajectory","title":"State-Only Imitation Learning by Trajectory Distribution Matching","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"transferring-hierarchical-structure-with-dual","title":"Transferring Hierarchical Structure with Dual Meta Imitation Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"what-would-the-expert-do-cdot-causal","title":"What Would the Expert $do(\\cdot)$?: Causal Imitation Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bottom-up-skill-discovery-from-unsegmented","title":"Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation","date":"2021-09-28","arxiv_id":"2109.13841","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-superoptimize-real-world-programs","title":"Learning to Superoptimize Real-world Programs","date":"2021-09-28","arxiv_id":"2109.13498","repositories_listed":0,"syntology":null},{"url":null,"slug":"safetynet-safe-planning-for-real-world-self","title":"SafetyNet: Safe planning for real-world self-driving vehicles using machine-learned policies","date":"2021-09-28","arxiv_id":"2109.13602","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-modeling-of-hand-object-interactions-1","title":"Dynamic Modeling of Hand-Object Interactions via Tactile Sensing.","date":"2021-09-27","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-relative-interactions-through","title":"Learning Relative Interactions through Imitation","date":"2021-09-24","arxiv_id":"2109.12013","repositories_listed":0,"syntology":null},{"url":null,"slug":"demonstration-efficient-guided-policy-search","title":"Demonstration-Efficient Guided Policy Search via Imitation of Robust Tube MPC","date":"2021-09-21","arxiv_id":"2109.09910","repositories_listed":0,"syntology":null},{"url":null,"slug":"thriftydagger-budget-aware-novelty-and-risk","title":"ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning","date":"2021-09-17","arxiv_id":"2109.08273","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-partially-observable-visual","title":"Deep Visual Navigation under Partial Observability","date":"2021-09-16","arxiv_id":"2109.07752","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-modeling-of-hand-object-interactions","title":"Dynamic Modeling of Hand-Object Interactions via Tactile Sensing","date":"2021-09-09","arxiv_id":"2109.04378","repositories_listed":0,"syntology":null},{"url":null,"slug":"fixing-exposure-bias-with-imitation-learning","title":"Fixing exposure bias with imitation learning needs powerful oracles","date":"2021-09-09","arxiv_id":"2109.04114","repositories_listed":0,"syntology":null},{"url":null,"slug":"behavioral-cloning-in-recurrent-spiking","title":"Error-based or target-based? A unifying framework for learning in recurrent spiking networks","date":"2021-09-02","arxiv_id":"2109.01039","repositories_listed":0,"syntology":null}],"record_sha256":"413d7d6ac8d67948b75e56bf5a184f63f22e4aeaf54ae150554091817b80fb54","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}