{"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/20","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":20,"pages_in_order":22,"rows_per_page":100,"rows":[1901,2000],"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/19","next":"/task/imitation-learning/papers/21","papers":[{"url":null,"slug":"cross-domain-imitation-learning-1","title":"Cross Domain Imitation Learning","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"goal-conditioned-video-prediction","title":"Goal-Conditioned Video Prediction","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-learning-of-robot-policies-using","title":"Imitation Learning of Robot Policies using Language, Vision and Motion","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-effective-exploration-strategies-for","title":"Learning Effective Exploration Strategies For Contextual Bandits","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-reach-goals-without-reinforcement","title":"Learning to Reach Goals Without Reinforcement Learning","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"moet-interpretable-and-verifiable-1","title":"MoET: Interpretable and Verifiable Reinforcement Learning via Mixture of Expert Trees","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"partial-simulation-for-imitation-learning","title":"Partial Simulation for Imitation Learning","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-optimization-by-local-improvement","title":"Policy Optimization by Local Improvement through Search","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"self-imitation-learning-via-trajectory","title":"Self-Imitation Learning via Trajectory-Conditioned Policy for Hard-Exploration Tasks","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"support-guided-adversarial-imitation-learning","title":"Support-guided Adversarial Imitation Learning","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-scalable-imitation-learning-for-multi","title":"Towards Scalable Imitation Learning for Multi-Agent Systems with Graph Neural Networks","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"190909906","title":"Leveraging Human Guidance for Deep Reinforcement Learning Tasks","date":"2019-09-21","arxiv_id":"1909.09906","repositories_listed":0,"syntology":null},{"url":null,"slug":"190909721","title":"Safer End-to-End Autonomous Driving via Conditional Imitation Learning and Command Augmentation","date":"2019-09-20","arxiv_id":"1909.09721","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-your-way-without-map-or-compass","title":"Learning Your Way Without Map or Compass: Panoramic Target Driven Visual Navigation","date":"2019-09-20","arxiv_id":"1909.09295","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-linearly-constrained-nonparametric","title":"A Linearly Constrained Nonparametric Framework for Imitation Learning","date":"2019-09-15","arxiv_id":"1909.07374","repositories_listed":0,"syntology":null},{"url":null,"slug":"state-representation-learning-from","title":"State Representation Learning from Demonstration","date":"2019-09-15","arxiv_id":"1910.01738","repositories_listed":0,"syntology":null},{"url":null,"slug":"vild-variational-imitation-learning-with","title":"VILD: Variational Imitation Learning with Diverse-quality Demonstrations","date":"2019-09-15","arxiv_id":"1909.06769","repositories_listed":0,"syntology":null},{"url":null,"slug":"correlation-priors-for-reinforcement-learning","title":"Correlation Priors for Reinforcement Learning","date":"2019-09-11","arxiv_id":"1909.05106","repositories_listed":0,"syntology":null},{"url":null,"slug":"expert-level-atari-imitation-learning-from","title":"Imitation Learning from Pixel-Level Demonstrations by HashReward","date":"2019-09-09","arxiv_id":"1909.03773","repositories_listed":0,"syntology":null},{"url":"/paper/imitation-learning-for-human-pose-prediction","slug":"imitation-learning-for-human-pose-prediction","title":"Imitation Learning for Human Pose Prediction","date":"2019-09-08","arxiv_id":"1909.03449","repositories_listed":0,"syntology":null},{"url":null,"slug":"mature-gail-imitation-learning-for-low-level","title":"Mature GAIL: Imitation Learning for Low-level and High-dimensional Input using Global Encoder and Cost Transformation","date":"2019-09-07","arxiv_id":"1909.03200","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-imitation-learning-a-privacy","title":"Federated Imitation Learning: A Privacy Considered Imitation Learning Framework for Cloud Robotic Systems with Heterogeneous Sensor Data","date":"2019-09-03","arxiv_id":"1909.00895","repositories_listed":0,"syntology":null},{"url":null,"slug":"conditional-vehicle-trajectories-prediction","title":"Conditional Vehicle Trajectories Prediction in CARLA Urban Environment","date":"2019-09-02","arxiv_id":"1909.00792","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-mr-to-ct-synthesis-for-petmr","title":"Improved MR to CT synthesis for PET/MR attenuation correction using Imitation Learning","date":"2019-08-21","arxiv_id":"1908.08431","repositories_listed":0,"syntology":null},{"url":null,"slug":"continuous-relaxation-of-symbolic-planner-for","title":"Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning","date":"2019-08-16","arxiv_id":"1908.06769","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-vision-based-flight-in-drone-swarms","title":"Learning Vision-based Flight in Drone Swarms by Imitation","date":"2019-08-08","arxiv_id":"1908.02999","repositories_listed":0,"syntology":null},{"url":null,"slug":"batch-recurrent-q-learning-for-backchannel","title":"Batch Recurrent Q-Learning for Backchannel Generation Towards Engaging Agents","date":"2019-08-06","arxiv_id":"1908.02037","repositories_listed":0,"syntology":null},{"url":null,"slug":"curiosity-driven-reinforcement-learning-for","title":"Curiosity-driven Reinforcement Learning for Diverse Visual Paragraph Generation","date":"2019-08-01","arxiv_id":"1908.00169","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-personalized","title":"Deep Reinforcement Learning for Personalized Search Story Recommendation","date":"2019-07-26","arxiv_id":"1907.11754","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-exploration-with-self-imitation","title":"Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards","date":"2019-07-24","arxiv_id":"1907.10247","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-goal-oriented-visual-dialog-agents","title":"Learning Goal-Oriented Visual Dialog Agents: Imitating and Surpassing Analytic Experts","date":"2019-07-24","arxiv_id":"1907.10500","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-data-driven-automatic-video-editing","title":"Towards Data-Driven Automatic Video Editing","date":"2019-07-17","arxiv_id":"1907.07345","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-reinforcement-learning-through","title":"Improved Reinforcement Learning through Imitation Learning Pretraining Towards Image-based Autonomous Driving","date":"2019-07-16","arxiv_id":"1907.06838","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-experience-in-lazy-search","title":"Leveraging Experience in Lazy Search","date":"2019-07-16","arxiv_id":"1907.07238","repositories_listed":0,"syntology":null},{"url":null,"slug":"environment-reconstruction-with-hidden","title":"Environment Reconstruction with Hidden Confounders for Reinforcement Learning based Recommendation","date":"2019-07-12","arxiv_id":"1907.06584","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-projected-policy-gradient-for","title":"Imitation-Projected Programmatic Reinforcement Learning","date":"2019-07-11","arxiv_id":"1907.05431","repositories_listed":0,"syntology":null},{"url":null,"slug":"utilizing-eye-gaze-to-enhance-the","title":"Utilizing Eye Gaze to Enhance the Generalization of Imitation Networks to Unseen Environments","date":"2019-07-10","arxiv_id":"1907.04728","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-policy-robot-imitation-learning-from-a","title":"On-Policy Robot Imitation Learning from a Converging Supervisor","date":"2019-07-08","arxiv_id":"1907.03423","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-a-behavioral-repertoire-from","title":"Learning a Behavioral Repertoire from Demonstrations","date":"2019-07-05","arxiv_id":"1907.03046","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-predictive-neural-machine","title":"Interactive-Predictive Neural Machine Translation through Reinforcement and Imitation","date":"2019-07-04","arxiv_id":"1907.02326","repositories_listed":0,"syntology":null},{"url":null,"slug":"integration-of-imitation-learning-using-gail","title":"Integration of Imitation Learning using GAIL and Reinforcement Learning using Task-achievement Rewards via Probabilistic Graphical Model","date":"2019-07-03","arxiv_id":"1907.02140","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-learning-within-constrained","title":"Active Learning within Constrained Environments through Imitation of an Expert Questioner","date":"2019-07-01","arxiv_id":"1907.00921","repositories_listed":0,"syntology":null},{"url":null,"slug":"sample-efficient-learning-of-path-following","title":"Sample Efficient Learning of Path Following and Obstacle Avoidance Behavior for Quadrotors","date":"2019-06-28","arxiv_id":"1906.12082","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-interactively-learn-and-assist","title":"Learning to Interactively Learn and Assist","date":"2019-06-24","arxiv_id":"1906.10187","repositories_listed":0,"syntology":null},{"url":null,"slug":"wasserstein-adversarial-imitation-learning","title":"Wasserstein Adversarial Imitation Learning","date":"2019-06-19","arxiv_id":"1906.08113","repositories_listed":0,"syntology":null},{"url":null,"slug":"radgrad-active-learning-with-loss-gradients","title":"RadGrad: Active learning with loss gradients","date":"2019-06-18","arxiv_id":"1906.07838","repositories_listed":0,"syntology":null},{"url":null,"slug":"ridm-reinforced-inverse-dynamics-modeling-for","title":"RIDM: Reinforced Inverse Dynamics Modeling for Learning from a Single Observed Demonstration","date":"2019-06-18","arxiv_id":"1906.07372","repositories_listed":0,"syntology":null},{"url":null,"slug":"sample-efficient-adversarial-imitation","title":"Sample-efficient Adversarial Imitation Learning from Observation","date":"2019-06-18","arxiv_id":"1906.07374","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-end-to-end-autonomous-driving","title":"Multimodal End-to-End Autonomous Driving","date":"2019-06-07","arxiv_id":"1906.03199","repositories_listed":0,"syntology":null},{"url":null,"slug":"watch-try-learn-meta-learning-from","title":"Watch, Try, Learn: Meta-Learning from Demonstrations and Reward","date":"2019-06-07","arxiv_id":"1906.03352","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-learning-for-non-autoregressive","title":"Imitation Learning for Non-Autoregressive Neural Machine Translation","date":"2019-06-05","arxiv_id":"1906.02041","repositories_listed":0,"syntology":null},{"url":null,"slug":"simultaneous-translation-with-flexible-policy","title":"Simultaneous Translation with Flexible Policy via Restricted Imitation Learning","date":"2019-06-04","arxiv_id":"1906.01135","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-exploitation-of-policy-imitation","title":"Adversarial Exploitation of Policy Imitation","date":"2019-06-03","arxiv_id":"1906.01121","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-learning-as-f-divergence","title":"Imitation Learning as $f$-Divergence Minimization","date":"2019-05-30","arxiv_id":"1905.12888","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-value-functions-and-the-agent-environment","title":"On Value Functions and the Agent-Environment Boundary","date":"2019-05-30","arxiv_id":"1905.13341","repositories_listed":0,"syntology":null},{"url":null,"slug":"recent-advances-in-imitation-learning-from","title":"Recent Advances in Imitation Learning from Observation","date":"2019-05-30","arxiv_id":"1905.13566","repositories_listed":0,"syntology":null},{"url":null,"slug":"lets-drive-driving-in-a-crowd-by-learning","title":"LeTS-Drive: Driving in a Crowd by Learning from Tree Search","date":"2019-05-29","arxiv_id":"1905.12197","repositories_listed":0,"syntology":null},{"url":null,"slug":"regression-via-kirszbraun-extension-with","title":"Efficient Kirszbraun Extension with Applications to Regression","date":"2019-05-28","arxiv_id":"1905.11930","repositories_listed":0,"syntology":null},{"url":"/paper/learning-to-reason-in-large-theories-without","slug":"learning-to-reason-in-large-theories-without","title":"Learning to Reason in Large Theories without Imitation","date":"2019-05-25","arxiv_id":"1905.10501","repositories_listed":0,"syntology":null},{"url":null,"slug":"action-assembly-sparse-imitation-learning-for","title":"Action Assembly: Sparse Imitation Learning for Text Based Games with Combinatorial Action Spaces","date":"2019-05-23","arxiv_id":"1905.09700","repositories_listed":0,"syntology":null},{"url":null,"slug":"where-to-find-next-passengers-on-e-hailing","title":"Optimal Passenger-Seeking Policies on E-hailing Platforms Using Markov Decision Process and Imitation Learning","date":"2019-05-23","arxiv_id":"1905.09906","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-learning-from-video-by-leveraging","title":"Imitation Learning from Video by Leveraging Proprioception","date":"2019-05-22","arxiv_id":"1905.09335","repositories_listed":0,"syntology":null},{"url":null,"slug":"goal-conditioned-imitation-learning-1","title":"Goal-conditioned Imitation Learning","date":"2019-05-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"randomized-adversarial-imitation-learning-for","title":"Randomized Adversarial Imitation Learning for Autonomous Driving","date":"2019-05-13","arxiv_id":"1905.05637","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-aware-data-aggregation-for-deep","title":"Uncertainty-Aware Data Aggregation for Deep Imitation Learning","date":"2019-05-07","arxiv_id":"1905.02780","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-exploration-strategy-for-self-1","title":"Adversarial Exploration Strategy for Self-Supervised Imitation Learning","date":"2019-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-from-noisy-demonstration-sets-via","title":"Learning from Noisy Demonstration Sets via Meta-Learned Suitability Assessor","date":"2019-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-drive-by-observing-the-best-and","title":"Learning to Drive by Observing the Best and Synthesizing the Worst","date":"2019-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-the-long-term-future-in-model-based","title":"Modeling the Long Term Future in Model-Based Reinforcement Learning","date":"2019-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforced-imitation-learning-from","title":"Reinforced Imitation Learning from Observations","date":"2019-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sample-efficient-imitation-learning-for","title":"Sample Efficient Imitation Learning for Continuous Control","date":"2019-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"simile-introducing-sequential-information","title":"SIMILE: Introducing Sequential Information towards More Effective Imitation Learning","date":"2019-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"trajectory-vae-for-multi-modal-imitation","title":"Trajectory VAE for multi-modal imitation","date":"2019-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-imitation-with-a-minimal-adversary","title":"Visual Imitation with a Minimal Adversary","date":"2019-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"gaze-training-by-modulated-dropout-improves","title":"Gaze Training by Modulated Dropout Improves Imitation Learning","date":"2019-04-17","arxiv_id":"1904.08377","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-supervision-for-robot-learning-via","title":"Efficient Supervision for Robot Learning via Imitation, Simulation, and Adaptation","date":"2019-04-15","arxiv_id":"1904.07346","repositories_listed":0,"syntology":null},{"url":null,"slug":"saliency-prediction-on-omnidirectional-images","title":"Saliency Prediction on Omnidirectional Images with Generative Adversarial Imitation Learning","date":"2019-04-15","arxiv_id":"1904.07080","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparison-of-policy-search-in-joint-space","title":"A Comparison of Policy Search in Joint Space and Cartesian Space for Refinement of Skills","date":"2019-04-14","arxiv_id":"1904.06765","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-bayesian-imitation-learning-with","title":"Few-Shot Bayesian Imitation Learning with Logical Program Policies","date":"2019-04-12","arxiv_id":"1904.06317","repositories_listed":0,"syntology":null},{"url":null,"slug":"improvisation-through-physical-understanding","title":"Improvisation through Physical Understanding: Using Novel Objects as Tools with Visual Foresight","date":"2019-04-11","arxiv_id":"1904.05538","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforced-imitation-in-heterogeneous-action","title":"Reinforced Imitation in Heterogeneous Action Space","date":"2019-04-06","arxiv_id":"1904.03438","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-predecessor-models-for-sample-1","title":"Generative predecessor models for sample-efficient imitation learning","date":"2019-04-01","arxiv_id":"1904.01139","repositories_listed":0,"syntology":null},{"url":null,"slug":"guided-meta-policy-search","title":"Guided Meta-Policy Search","date":"2019-04-01","arxiv_id":"1904.00956","repositories_listed":0,"syntology":null},{"url":null,"slug":"cortical-mirror-system-activation-during-real","title":"Cortical Mirror-System Activation During Real-Life Game Playing: An Intracranial Electroencephalography (EEG) Study","date":"2019-03-27","arxiv_id":"1902.09189","repositories_listed":0,"syntology":null},{"url":null,"slug":"hindsight-generative-adversarial-imitation","title":"Hindsight Generative Adversarial Imitation Learning","date":"2019-03-19","arxiv_id":"1903.07854","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-imitating-visual-attention-of-experts","title":"Toward Imitating Visual Attention of Experts in Software Development Tasks","date":"2019-03-15","arxiv_id":"1903.06320","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-learning-of-factored-multi-agent","title":"Imitation Learning of Factored Multi-agent Reactive Models","date":"2019-03-12","arxiv_id":"1903.04714","repositories_listed":0,"syntology":null},{"url":null,"slug":"dyna-ail-adversarial-imitation-learning-by","title":"Dyna-AIL : Adversarial Imitation Learning by Planning","date":"2019-03-08","arxiv_id":"1903.03234","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-dynamics-model-in-reinforcement","title":"Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future","date":"2019-03-05","arxiv_id":"1903.01599","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-aware-imitation-learning-using","title":"Uncertainty-Aware Imitation Learning using Kernelized Movement Primitives","date":"2019-03-05","arxiv_id":"1903.02114","repositories_listed":0,"syntology":null},{"url":null,"slug":"grp-model-for-sensorimotor-learning","title":"GRP Model for Sensorimotor Learning","date":"2019-03-01","arxiv_id":"1903.00568","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-a-family-of-optimal-state-feedback","title":"Learning Dynamic-Objective Policies from a Class of Optimal Trajectories","date":"2019-02-27","arxiv_id":"1902.10139","repositories_listed":0,"syntology":null},{"url":null,"slug":"simultaneously-learning-vision-and-feature","title":"Simultaneously Learning Vision and Feature-based Control Policies for Real-world Ball-in-a-Cup","date":"2019-02-13","arxiv_id":"1902.04706","repositories_listed":0,"syntology":null},{"url":null,"slug":"cesma-centralized-expert-supervises-multi","title":"Decentralized Multi-Agents by Imitation of a Centralized Controller","date":"2019-02-06","arxiv_id":"1902.02311","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-learning-from-imperfect","title":"Imitation Learning from Imperfect Demonstration","date":"2019-01-27","arxiv_id":"1901.09387","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-function-approximation-for","title":"Evaluation Function Approximation for Scrabble","date":"2019-01-25","arxiv_id":"1901.08728","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-reinforcement-learning-for-multi","title":"Hierarchical Reinforcement Learning for Multi-agent MOBA Game","date":"2019-01-23","arxiv_id":"1901.08004","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-learning-for-contextual-bandit","title":"Meta-Learning for Contextual Bandit Exploration","date":"2019-01-23","arxiv_id":"1901.08159","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-imitation-learning-with-recurrent","title":"Towards Learning to Imitate from a Single Video Demonstration","date":"2019-01-22","arxiv_id":"1901.07186","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-global-convergence-of-imitation","title":"On the Global Convergence of Imitation Learning: A Case for Linear Quadratic Regulator","date":"2019-01-11","arxiv_id":"1901.03674","repositories_listed":0,"syntology":null}],"record_sha256":"cdc59c2d647a8bd6416861ab85d4e5597cb9d5a5046a86bbab0ddecfaea88836","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}