{"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/7","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":7,"pages_in_order":22,"rows_per_page":100,"rows":[601,700],"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/6","next":"/task/imitation-learning/papers/8","papers":[{"url":"/paper/compositional-plan-vectors","slug":"compositional-plan-vectors","title":"Compositional Plan Vectors","date":"2019-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/smile-scalable-meta-inverse-reinforcement","slug":"smile-scalable-meta-inverse-reinforcement","title":"SMILe: Scalable Meta Inverse Reinforcement Learning through Context-Conditional Policies","date":"2019-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/third-person-visual-imitation-learning-via-1","slug":"third-person-visual-imitation-learning-via-1","title":"Third-Person Visual Imitation Learning via Decoupled Hierarchical Controller","date":"2019-11-21","arxiv_id":"1911.09676","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/third-person-visual-imitation-learning-via-1#ran","syntology_url":"https://syntology.ai/paper/1911.09676","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.09676"}},"official":{"repos":["pathak22/hierarchical-imitation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-one-shot-imitation-from-humans","slug":"learning-one-shot-imitation-from-humans","title":"Learning One-Shot Imitation from Humans without Humans","date":"2019-11-04","arxiv_id":"1911.01103","repositories_listed":1,"syntology":null},{"url":"/paper/learning-from-trajectories-via-subgoal-1","slug":"learning-from-trajectories-via-subgoal-1","title":"Learning from Trajectories via Subgoal Discovery","date":"2019-11-03","arxiv_id":"1911.07224","repositories_listed":1,"syntology":null},{"url":"/paper/positive-unlabeled-reward-learning","slug":"positive-unlabeled-reward-learning","title":"Positive-Unlabeled Reward Learning","date":"2019-11-01","arxiv_id":"1911.00459","repositories_listed":1,"syntology":null},{"url":"/paper/learning-latent-process-from-high-dimensional","slug":"learning-latent-process-from-high-dimensional","title":"Learning Latent Process from High-Dimensional Event Sequences via Efficient Sampling","date":"2019-10-28","arxiv_id":"1910.12469","repositories_listed":1,"syntology":null},{"url":"/paper/bail-best-action-imitation-learning-for-batch-1","slug":"bail-best-action-imitation-learning-for-batch-1","title":"BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning","date":"2019-10-27","arxiv_id":"1910.12179","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bail-best-action-imitation-learning-for-batch-1#ran","syntology_url":"https://syntology.ai/paper/1910.12179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.12179"}},"official":{"repos":["lanyavik/BAIL"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/relay-policy-learning-solving-long-horizon","slug":"relay-policy-learning-solving-long-horizon","title":"Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning","date":"2019-10-25","arxiv_id":"1910.11956","repositories_listed":1,"syntology":null},{"url":"/paper/model-based-behavioral-cloning-with-future","slug":"model-based-behavioral-cloning-with-future","title":"Model-based Behavioral Cloning with Future Image Similarity Learning","date":"2019-10-08","arxiv_id":"1910.03157","repositories_listed":1,"syntology":null},{"url":"/paper/cross-domain-imitation-learning","slug":"cross-domain-imitation-learning","title":"Domain Adaptive Imitation Learning","date":"2019-09-30","arxiv_id":"1910.00105","repositories_listed":1,"syntology":null},{"url":"/paper/interaction-dataset-an-international","slug":"interaction-dataset-an-international","title":"INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Maps","date":"2019-09-30","arxiv_id":"1910.03088","repositories_listed":1,"syntology":null},{"url":"/paper/accept-synthetic-objects-as-real-end-to-end","slug":"accept-synthetic-objects-as-real-end-to-end","title":"Accept Synthetic Objects as Real: End-to-End Training of Attentive Deep Visuomotor Policies for Manipulation in Clutter","date":"2019-09-24","arxiv_id":"1909.11128","repositories_listed":1,"syntology":null},{"url":"/paper/avoidance-learning-using-observational","slug":"avoidance-learning-using-observational","title":"Avoidance Learning Using Observational Reinforcement Learning","date":"2019-09-24","arxiv_id":"1909.11228","repositories_listed":1,"syntology":null},{"url":"/paper/deep-imitation-learning-of-sequential-fabric","slug":"deep-imitation-learning-of-sequential-fabric","title":"Deep Imitation Learning of Sequential Fabric Smoothing From an Algorithmic Supervisor","date":"2019-09-23","arxiv_id":"1910.04854","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-correspondence-in-visuomotor","slug":"self-supervised-correspondence-in-visuomotor","title":"Self-Supervised Correspondence in Visuomotor Policy Learning","date":"2019-09-16","arxiv_id":"1909.06933","repositories_listed":1,"syntology":null},{"url":"/paper/deep-attention-networks-reveal-the-rules-of","slug":"deep-attention-networks-reveal-the-rules-of","title":"Deep attention networks reveal the rules of collective motion in zebrafish","date":"2019-09-13","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mpc-net-a-first-principles-guided-policy","slug":"mpc-net-a-first-principles-guided-policy","title":"MPC-Net: A First Principles Guided Policy Search","date":"2019-09-11","arxiv_id":"1909.05197","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mpc-net-a-first-principles-guided-policy#ran","syntology_url":"https://syntology.ai/paper/1909.05197","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.05197"}},"official":{"repos":["leggedrobotics/MPC-Net"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/help-anna-visual-navigation-with-natural","slug":"help-anna-visual-navigation-with-natural","title":"Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learning","date":"2019-09-04","arxiv_id":"1909.01871","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-comparison-on-imitation-learning","slug":"an-empirical-comparison-on-imitation-learning","title":"An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generation","date":"2019-08-28","arxiv_id":"1908.10835","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/an-empirical-comparison-on-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/1908.10835","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.10835"}},"official":{"repos":["ddddwy/Reinforce-Paraphrase-Generation"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/imitation-learning-for-sentence-generation","slug":"imitation-learning-for-sentence-generation","title":"Imitation Learning for Sentence Generation with Dilated Convolutions Using Adversarial Training","date":"2019-08-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/comyco-quality-aware-adaptive-video-streaming","slug":"comyco-quality-aware-adaptive-video-streaming","title":"Comyco: Quality-Aware Adaptive Video Streaming via Imitation Learning","date":"2019-08-06","arxiv_id":"1908.02270","repositories_listed":1,"syntology":null},{"url":"/paper/combining-learned-skills-and-reinforcement","slug":"combining-learned-skills-and-reinforcement","title":"Learning to combine primitive skills: A step towards versatile robotic manipulation","date":"2019-08-02","arxiv_id":"1908.00722","repositories_listed":1,"syntology":null},{"url":"/paper/self-imitation-learning-of-locomotion","slug":"self-imitation-learning-of-locomotion","title":"Self-Imitation Learning of Locomotion Movements through Termination Curriculum","date":"2019-07-27","arxiv_id":"1907.11842","repositories_listed":1,"syntology":null},{"url":"/paper/muscle-actuated-human-simulation-and-control","slug":"muscle-actuated-human-simulation-and-control","title":"Muscle-actuated Human Simulation and Control","date":"2019-07-23","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-self-correctable-policies-and-value","slug":"learning-self-correctable-policies-and-value","title":"Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling","date":"2019-07-12","arxiv_id":"1907.05634","repositories_listed":1,"syntology":null},{"url":"/paper/hybrid-system-identification-using-switching","slug":"hybrid-system-identification-using-switching","title":"Hybrid system identification using switching density networks","date":"2019-07-09","arxiv_id":"1907.04360","repositories_listed":1,"syntology":null},{"url":"/paper/co-training-for-policy-learning","slug":"co-training-for-policy-learning","title":"Co-training for Policy Learning","date":"2019-07-03","arxiv_id":"1907.04484","repositories_listed":1,"syntology":null},{"url":"/paper/pyrep-bringing-v-rep-to-deep-robot-learning","slug":"pyrep-bringing-v-rep-to-deep-robot-learning","title":"PyRep: Bringing V-REP to Deep Robot Learning","date":"2019-06-26","arxiv_id":"1906.11176","repositories_listed":1,"syntology":null},{"url":"/paper/learning-belief-representations-for-imitation","slug":"learning-belief-representations-for-imitation","title":"Learning Belief Representations for Imitation Learning in POMDPs","date":"2019-06-22","arxiv_id":"1906.09510","repositories_listed":1,"syntology":null},{"url":"/paper/goal-conditioned-imitation-learning","slug":"goal-conditioned-imitation-learning","title":"Goal-conditioned Imitation Learning","date":"2019-06-13","arxiv_id":"1906.05838","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/goal-conditioned-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/1906.05838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.05838"}},"official":{"repos":["dingyiming0427/goalgail"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-of-spatio-temporal","slug":"reinforcement-learning-of-spatio-temporal","title":"Imitation Learning of Neural Spatio-Temporal Point Processes","date":"2019-06-13","arxiv_id":"1906.05467","repositories_listed":1,"syntology":null},{"url":"/paper/wasserstein-reinforcement-learning","slug":"wasserstein-reinforcement-learning","title":"Learning to Score Behaviors for Guided Policy Optimization","date":"2019-06-11","arxiv_id":"1906.04349","repositories_listed":1,"syntology":null},{"url":"/paper/an-imitation-learning-approach-to","slug":"an-imitation-learning-approach-to","title":"An Imitation Learning Approach to Unsupervised Parsing","date":"2019-06-05","arxiv_id":"1906.02276","repositories_listed":1,"syntology":null},{"url":"/paper/pay-attention-robustifying-a-deep-visuomotor-1","slug":"pay-attention-robustifying-a-deep-visuomotor-1","title":"Pay Attention! - Robustifying a Deep Visuomotor Policy Through Task-Focused Visual Attention","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/exploring-computational-user-models-for-agent","slug":"exploring-computational-user-models-for-agent","title":"Exploring Computational User Models for Agent Policy Summarization","date":"2019-05-30","arxiv_id":"1905.13271","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-imitation-learning-from","slug":"adversarial-imitation-learning-from","title":"Adversarial Imitation Learning from Incomplete Demonstrations","date":"2019-05-29","arxiv_id":"1905.12310","repositories_listed":1,"syntology":null},{"url":"/paper/provably-efficient-imitation-learning-from","slug":"provably-efficient-imitation-learning-from","title":"Provably Efficient Imitation Learning from Observation Alone","date":"2019-05-27","arxiv_id":"1905.10948","repositories_listed":1,"syntology":null},{"url":"/paper/a-data-driven-approach-for-motion-planning-of","slug":"a-data-driven-approach-for-motion-planning-of","title":"Efficient Motion Planning for Automated Lane Change based on Imitation Learning and Mixed-Integer Optimization","date":"2019-04-18","arxiv_id":"1904.08784","repositories_listed":1,"syntology":null},{"url":"/paper/atari-head-atari-human-eye-tracking-and","slug":"atari-head-atari-human-eye-tracking-and","title":"Atari-HEAD: Atari Human Eye-Tracking and Demonstration Dataset","date":"2019-03-15","arxiv_id":"1903.06754","repositories_listed":1,"syntology":null},{"url":"/paper/simulating-emergent-properties-of-human","slug":"simulating-emergent-properties-of-human","title":"Simulating Emergent Properties of Human Driving Behavior Using Multi-Agent Reward Augmented Imitation Learning","date":"2019-03-14","arxiv_id":"1903.05766","repositories_listed":1,"syntology":null},{"url":"/paper/hybrid-reinforcement-learning-with-expert","slug":"hybrid-reinforcement-learning-with-expert","title":"Hybrid Reinforcement Learning with Expert State Sequences","date":"2019-03-11","arxiv_id":"1903.04110","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hybrid-reinforcement-learning-with-expert#ran","syntology_url":"https://syntology.ai/paper/1903.04110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.04110"}},"official":{"repos":["XiaoxiaoGuo/tensor4rl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/modeling-social-group-communication-with","slug":"modeling-social-group-communication-with","title":"MGpi: A Computational Model of Multiagent Group Perception and Interaction","date":"2019-03-04","arxiv_id":"1903.01537","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-driving-deploying-through","slug":"end-to-end-driving-deploying-through","title":"Visual-based Autonomous Driving Deployment from a Stochastic and Uncertainty-aware Perspective","date":"2019-03-03","arxiv_id":"1903.00821","repositories_listed":1,"syntology":null},{"url":"/paper/prolonets-neural-encoding-human-experts","slug":"prolonets-neural-encoding-human-experts","title":"Neural-encoding Human Experts' Domain Knowledge to Warm Start Reinforcement Learning","date":"2019-02-15","arxiv_id":"1902.06007","repositories_listed":1,"syntology":null},{"url":"/paper/artificial-intelligence-for-prosthetics","slug":"artificial-intelligence-for-prosthetics","title":"Artificial Intelligence for Prosthetics - challenge solutions","date":"2019-02-07","arxiv_id":"1902.02441","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/artificial-intelligence-for-prosthetics#ran","syntology_url":"https://syntology.ai/paper/1902.02441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.02441"}},"official":{"repos":["iasawseen/MultiServerRL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/non-monotonic-sequential-text-generation","slug":"non-monotonic-sequential-text-generation","title":"Non-Monotonic Sequential Text Generation","date":"2019-02-05","arxiv_id":"1902.02192","repositories_listed":1,"syntology":null},{"url":"/paper/naomi-non-autoregressive-multiresolution","slug":"naomi-non-autoregressive-multiresolution","title":"NAOMI: Non-Autoregressive Multiresolution Sequence Imputation","date":"2019-01-30","arxiv_id":"1901.10946","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/naomi-non-autoregressive-multiresolution#ran","syntology_url":"https://syntology.ai/paper/1901.10946","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.10946"}},"official":{"repos":["felixykliu/NAOMI"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/amplifying-the-imitation-effect-for","slug":"amplifying-the-imitation-effect-for","title":"Amplifying the Imitation Effect for Reinforcement Learning of UCAV's Mission Execution","date":"2019-01-17","arxiv_id":"1901.05856","repositories_listed":1,"syntology":null},{"url":"/paper/transfer-learning-for-prosthetics-using","slug":"transfer-learning-for-prosthetics-using","title":"Transfer Learning for Prosthetics Using Imitation Learning","date":"2019-01-15","arxiv_id":"1901.04772","repositories_listed":1,"syntology":null},{"url":"/paper/vision-based-navigation-with-language-based","slug":"vision-based-navigation-with-language-based","title":"Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Intervention","date":"2018-12-10","arxiv_id":"1812.04155","repositories_listed":1,"syntology":null},{"url":"/paper/dialogue-generation-from-imitation-learning","slug":"dialogue-generation-from-imitation-learning","title":"Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning","date":"2018-12-09","arxiv_id":"1812.03509","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-stability-analysis-of-optimal-state","slug":"on-the-stability-analysis-of-optimal-state","title":"On the stability analysis of deep neural network representations of an optimal state-feedback","date":"2018-12-06","arxiv_id":"1812.02532","repositories_listed":1,"syntology":null},{"url":"/paper/exponentially-weighted-imitation-learning-for","slug":"exponentially-weighted-imitation-learning-for","title":"Exponentially Weighted Imitation Learning for Batched Historical Data","date":"2018-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/guiding-policies-with-language-via-meta","slug":"guiding-policies-with-language-via-meta","title":"Guiding Policies with Language via Meta-Learning","date":"2018-11-19","arxiv_id":"1811.07882","repositories_listed":1,"syntology":null},{"url":"/paper/mapping-navigation-instructions-to-continuous","slug":"mapping-navigation-instructions-to-continuous","title":"Mapping Navigation Instructions to Continuous Control Actions with Position-Visitation Prediction","date":"2018-11-10","arxiv_id":"1811.04179","repositories_listed":1,"syntology":null},{"url":"/paper/a-dynamic-regret-analysis-and-adaptive","slug":"a-dynamic-regret-analysis-and-adaptive","title":"Dynamic Regret Convergence Analysis and an Adaptive Regularization Algorithm for On-Policy Robot Imitation Learning","date":"2018-11-06","arxiv_id":"1811.02184","repositories_listed":1,"syntology":null},{"url":"/paper/learning-beam-search-policies-via-imitation","slug":"learning-beam-search-policies-via-imitation","title":"Learning Beam Search Policies via Imitation Learning","date":"2018-11-01","arxiv_id":"1811.00512","repositories_listed":1,"syntology":null},{"url":"/paper/efficiently-combining-human-demonstrations","slug":"efficiently-combining-human-demonstrations","title":"Efficiently Combining Human Demonstrations and Interventions for Safe Training of Autonomous Systems in Real-Time","date":"2018-10-26","arxiv_id":"1810.11545","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/efficiently-combining-human-demonstrations#ran","syntology_url":"https://syntology.ai/paper/1810.11545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.11545"}},"official":null}},{"url":"/paper/deep-imitative-models-for-flexible-inference","slug":"deep-imitative-models-for-flexible-inference","title":"Deep Imitative Models for Flexible Inference, Planning, and Control","date":"2018-10-15","arxiv_id":"1810.06544","repositories_listed":1,"syntology":null},{"url":"/paper/predictor-corrector-policy-optimization","slug":"predictor-corrector-policy-optimization","title":"Predictor-Corrector Policy Optimization","date":"2018-10-15","arxiv_id":"1810.06509","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/predictor-corrector-policy-optimization#ran","syntology_url":"https://syntology.ai/paper/1810.06509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.06509"}},"official":{"repos":["gtrll/rlfamily"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/task-oriented-hand-motion-retargeting-for","slug":"task-oriented-hand-motion-retargeting-for","title":"Task-Oriented Hand Motion Retargeting for Dexterous Manipulation Imitation","date":"2018-10-03","arxiv_id":"1810.01845","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/task-oriented-hand-motion-retargeting-for#ran","syntology_url":"https://syntology.ai/paper/1810.01845","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.01845"}},"official":{"repos":["DaphneAntotsiou/task-oriented-hand-retargeting"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/imitation-learning-for-neural-morphological","slug":"imitation-learning-for-neural-morphological","title":"Imitation Learning for Neural Morphological String Transduction","date":"2018-08-31","arxiv_id":"1808.10701","repositories_listed":1,"syntology":null},{"url":"/paper/multi-agent-generative-adversarial-imitation","slug":"multi-agent-generative-adversarial-imitation","title":"Multi-Agent Generative Adversarial Imitation Learning","date":"2018-07-26","arxiv_id":"1807.09936","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-agent-generative-adversarial-imitation#ran","syntology_url":"https://syntology.ai/paper/1807.09936","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.09936"}},"official":null}},{"url":"/paper/generative-adversarial-imitation-from","slug":"generative-adversarial-imitation-from","title":"Generative Adversarial Imitation from Observation","date":"2018-07-17","arxiv_id":"1807.06158","repositories_listed":1,"syntology":null},{"url":"/paper/learning-how-to-actively-learn-a-deep","slug":"learning-how-to-actively-learn-a-deep","title":"Learning How to Actively Learn: A Deep Imitation Learning Approach","date":"2018-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/universal-planning-networks-learning","slug":"universal-planning-networks-learning","title":"Universal Planning Networks: Learning Generalizable Representations for Visuomotor Control","date":"2018-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/conditional-affordance-learning-for-driving","slug":"conditional-affordance-learning-for-driving","title":"Conditional Affordance Learning for Driving in Urban Environments","date":"2018-06-18","arxiv_id":"1806.06498","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":11,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/conditional-affordance-learning-for-driving#ran","syntology_url":"https://syntology.ai/paper/1806.06498","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.06498"}},"official":{"repos":["xl-sr/CAL"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/following-high-level-navigation-instructions","slug":"following-high-level-navigation-instructions","title":"Following High-level Navigation Instructions on a Simulated Quadcopter with Imitation Learning","date":"2018-05-31","arxiv_id":"1806.00047","repositories_listed":1,"syntology":null},{"url":"/paper/multi-task-maximum-entropy-inverse","slug":"multi-task-maximum-entropy-inverse","title":"Multi-task Maximum Entropy Inverse Reinforcement Learning","date":"2018-05-22","arxiv_id":"1805.08882","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multi-task-maximum-entropy-inverse#ran","syntology_url":"https://syntology.ai/paper/1805.08882","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.08882"}},"official":{"repos":["HumanCompatibleAI/population-irl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-shot-visual-imitation","slug":"zero-shot-visual-imitation","title":"Zero-Shot Visual Imitation","date":"2018-04-23","arxiv_id":"1804.08606","repositories_listed":1,"syntology":null},{"url":"/paper/dialogue-learning-with-human-teaching-and","slug":"dialogue-learning-with-human-teaching-and","title":"Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems","date":"2018-04-18","arxiv_id":"1804.06512","repositories_listed":1,"syntology":null},{"url":"/paper/universal-planning-networks","slug":"universal-planning-networks","title":"Universal Planning Networks","date":"2018-04-02","arxiv_id":"1804.00645","repositories_listed":1,"syntology":null},{"url":"/paper/visual-robot-task-planning","slug":"visual-robot-task-planning","title":"Visual Robot Task Planning","date":"2018-03-30","arxiv_id":"1804.00062","repositories_listed":1,"syntology":null},{"url":"/paper/multi-agent-imitation-learning-for-driving","slug":"multi-agent-imitation-learning-for-driving","title":"Multi-Agent Imitation Learning for Driving Simulation","date":"2018-03-02","arxiv_id":"1803.01044","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-and-imitation-learning-for","slug":"reinforcement-and-imitation-learning-for","title":"Reinforcement and Imitation Learning for Diverse Visuomotor Skills","date":"2018-02-26","arxiv_id":"1802.09564","repositories_listed":1,"syntology":null},{"url":"/paper/carla-an-open-urban-driving-simulator","slug":"carla-an-open-urban-driving-simulator","title":"CARLA: An Open Urban Driving Simulator","date":"2017-11-10","arxiv_id":"1711.03938","repositories_listed":1,"syntology":null},{"url":"/paper/socially-compliant-navigation-through-raw","slug":"socially-compliant-navigation-through-raw","title":"Socially Compliant Navigation through Raw Depth Inputs with Generative Adversarial Imitation Learning","date":"2017-10-06","arxiv_id":"1710.02543","repositories_listed":1,"syntology":null},{"url":"/paper/optiongan-learning-joint-reward-policy","slug":"optiongan-learning-joint-reward-policy","title":"OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learning","date":"2017-09-20","arxiv_id":"1709.06683","repositories_listed":1,"syntology":null},{"url":"/paper/stardata-a-starcraft-ai-research-dataset","slug":"stardata-a-starcraft-ai-research-dataset","title":"STARDATA: A StarCraft AI Research Dataset","date":"2017-08-07","arxiv_id":"1708.02139","repositories_listed":1,"syntology":null},{"url":"/paper/rail-risk-averse-imitation-learning","slug":"rail-risk-averse-imitation-learning","title":"RAIL: Risk-Averse Imitation Learning","date":"2017-07-20","arxiv_id":"1707.06658","repositories_listed":1,"syntology":null},{"url":"/paper/merge-or-not-learning-to-group-faces-via","slug":"merge-or-not-learning-to-group-faces-via","title":"Merge or Not? Learning to Group Faces via Imitation Learning","date":"2017-07-13","arxiv_id":"1707.03986","repositories_listed":1,"syntology":null},{"url":"/paper/imitation-from-observation-learning-to","slug":"imitation-from-observation-learning-to","title":"Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation","date":"2017-07-11","arxiv_id":"1707.03374","repositories_listed":1,"syntology":null},{"url":"/paper/learning-human-behaviors-from-motion-capture","slug":"learning-human-behaviors-from-motion-capture","title":"Learning human behaviors from motion capture by adversarial imitation","date":"2017-07-07","arxiv_id":"1707.02201","repositories_listed":1,"syntology":null},{"url":"/paper/gated-attention-architectures-for-task","slug":"gated-attention-architectures-for-task","title":"Gated-Attention Architectures for Task-Oriented Language Grounding","date":"2017-06-22","arxiv_id":"1706.07230","repositories_listed":1,"syntology":null},{"url":"/paper/optimizing-differentiable-relaxations-of","slug":"optimizing-differentiable-relaxations-of","title":"Optimizing Differentiable Relaxations of Coreference Evaluation Metrics","date":"2017-04-14","arxiv_id":"1704.04451","repositories_listed":1,"syntology":null},{"url":"/paper/third-person-imitation-learning","slug":"third-person-imitation-learning","title":"Third-Person Imitation Learning","date":"2017-03-06","arxiv_id":"1703.01703","repositories_listed":1,"syntology":null},{"url":"/paper/imitating-driver-behavior-with-generative","slug":"imitating-driver-behavior-with-generative","title":"Imitating Driver Behavior with Generative Adversarial Networks","date":"2017-01-24","arxiv_id":"1701.06699","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-of-deep-network-solutions-for","slug":"a-survey-of-deep-network-solutions-for","title":"A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation","date":"2016-12-21","arxiv_id":"1612.07139","repositories_listed":1,"syntology":null},{"url":"/paper/query-efficient-imitation-learning-for-end-to","slug":"query-efficient-imitation-learning-for-end-to","title":"Query-Efficient Imitation Learning for End-to-End Autonomous Driving","date":"2016-05-20","arxiv_id":"1605.06450","repositories_listed":1,"syntology":null},{"url":"/paper/imitation-learning-of-agenda-based-semantic","slug":"imitation-learning-of-agenda-based-semantic","title":"Imitation Learning of Agenda-based Semantic Parsers","date":"2015-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"supervised-fine-tuning-on-curated-data-is","title":"Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)","date":"2025-07-17","arxiv_id":"2507.12856","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-imitation-game-turing-machine-imitator-is","title":"The Imitation Game: Turing Machine Imitator is Length Generalizable Reasoner","date":"2025-07-17","arxiv_id":"2507.13332","repositories_listed":0,"syntology":null},{"url":null,"slug":"ec-flow-enabling-versatile-robotic","title":"EC-Flow: Enabling Versatile Robotic Manipulation from Action-Unlabeled Videos via Embodiment-Centric Flow","date":"2025-07-08","arxiv_id":"2507.06224","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-bilateral-teleoperation-and-imitation","title":"Fast Bilateral Teleoperation and Imitation Learning Using Sensorless Force Control via Accurate Dynamics Model","date":"2025-07-08","arxiv_id":"2507.06174","repositories_listed":0,"syntology":null},{"url":null,"slug":"lead-the-llm-enhanced-planning-system","title":"LeAD: The LLM Enhanced Planning System Converged with End-to-end Autonomous Driving","date":"2025-07-08","arxiv_id":"2507.05754","repositories_listed":0,"syntology":null},{"url":null,"slug":"world-aware-planning-narratives-enhance-large","title":"World-aware Planning Narratives Enhance Large Vision-Language Model Planner","date":"2025-06-26","arxiv_id":"2506.21230","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-expert-performance-with-limited","title":"Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration","date":"2025-06-25","arxiv_id":"2506.20307","repositories_listed":0,"syntology":null},{"url":null,"slug":"ark-an-open-source-python-based-framework-for","title":"Ark: An Open-source Python-based Framework for Robot Learning","date":"2025-06-24","arxiv_id":"2506.21628","repositories_listed":0,"syntology":null},{"url":null,"slug":"codediffuser-attention-enhanced-diffusion","title":"CodeDiffuser: Attention-Enhanced Diffusion Policy via VLM-Generated Code for Instruction Ambiguity","date":"2025-06-19","arxiv_id":"2506.16652","repositories_listed":0,"syntology":null}],"record_sha256":"f552991523439e92ae3fe576ce32f3ef423941d0749dafcbadc0b70d3dc6a120","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}