{"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/21","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":21,"pages_in_order":22,"rows_per_page":100,"rows":[2001,2100],"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/20","next":"/task/imitation-learning/papers/22","papers":[{"url":null,"slug":"learning-the-optimal-state-feedback-via","title":"Learning the optimal state-feedback via supervised imitation learning","date":"2019-01-07","arxiv_id":"1901.02369","repositories_listed":0,"syntology":null},{"url":null,"slug":"lora-learning-to-optimize-for-resource","title":"LORM: Learning to Optimize for Resource Management in Wireless Networks with Few Training Samples","date":"2018-12-18","arxiv_id":"1812.07998","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-learning-for-end-to-end-vehicle","title":"Imitation Learning for End to End Vehicle Longitudinal Control with Forward Camera","date":"2018-12-14","arxiv_id":"1812.05841","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-adversarial-self-imitation","title":"Generative Adversarial Self-Imitation Learning","date":"2018-12-03","arxiv_id":"1812.00950","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-bayesian-approach-to-generative-adversarial","title":"A Bayesian Approach to Generative Adversarial Imitation Learning","date":"2018-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"discovering-hierarchies-using-imitation","title":"Discovering hierarchies using Imitation Learning from hierarchy aware policies","date":"2018-12-01","arxiv_id":"1812.00225","repositories_listed":0,"syntology":null},{"url":null,"slug":"blockpuzzle-a-challenge-in-physical-reasoning","title":"BlockPuzzle - A Challenge in Physical Reasoning and Generalization for Robot Learning","date":"2018-11-30","arxiv_id":"1812.00091","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-finite-state-representations-of","title":"Learning Finite State Representations of Recurrent Policy Networks","date":"2018-11-29","arxiv_id":"1811.12530","repositories_listed":0,"syntology":null},{"url":"/paper/reinforced-cross-modal-matching-and-self","slug":"reinforced-cross-modal-matching-and-self","title":"Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation","date":"2018-11-25","arxiv_id":"1811.10092","repositories_listed":0,"syntology":null},{"url":null,"slug":"connecting-the-dots-between-mle-and-rl-for","title":"Connecting the Dots Between MLE and RL for Sequence Prediction","date":"2018-11-24","arxiv_id":"1811.09740","repositories_listed":0,"syntology":null},{"url":null,"slug":"early-fusion-for-goal-directed-robotic-vision","title":"Early Fusion for Goal Directed Robotic Vision","date":"2018-11-21","arxiv_id":"1811.08824","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-algorithmic-perspective-on-imitation","title":"An Algorithmic Perspective on Imitation Learning","date":"2018-11-16","arxiv_id":"1811.06711","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-compensate-photovoltaic-power","title":"Learning to Compensate Photovoltaic Power Fluctuations from Images of the Sky by Imitating an Optimal Policy","date":"2018-11-13","arxiv_id":"1811.05788","repositories_listed":0,"syntology":null},{"url":null,"slug":"roboturk-a-crowdsourcing-platform-for-robotic","title":"RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation","date":"2018-11-07","arxiv_id":"1811.02790","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-defense-by-learning-to-attack","title":"Learning to Defend by Learning to Attack","date":"2018-11-03","arxiv_id":"1811.01213","repositories_listed":0,"syntology":null},{"url":null,"slug":"approximate-dynamic-oracle-for-dependency","title":"Approximate Dynamic Oracle for Dependency Parsing with Reinforcement Learning","date":"2018-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"navigation-by-imitation-in-a-pedestrian-rich","title":"Navigation by Imitation in a Pedestrian-Rich Environment","date":"2018-11-01","arxiv_id":"1811.00506","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-shot-hierarchical-imitation-learning-of","title":"One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks","date":"2018-10-25","arxiv_id":"1810.11043","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-imitation-gan-learning-control-policies","title":"Injective State-Image Mapping facilitates Visual Adversarial Imitation Learning","date":"2018-10-02","arxiv_id":"1810.01108","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-agent-modeling-by-learning-to","title":"Interactive Agent Modeling by Learning to Probe","date":"2018-10-01","arxiv_id":"1810.00510","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-actively-learn-neural-machine","title":"Learning to Actively Learn Neural Machine Translation","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"uzh-at-conll-sigmorphon-2018-shared-task-on","title":"UZH at CoNLL--SIGMORPHON 2018 Shared Task on Universal Morphological Reinflection","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"directed-info-gail-learning-hierarchical","title":"Directed-Info GAIL: Learning Hierarchical Policies from Unsegmented Demonstrations using Directed Information","date":"2018-09-29","arxiv_id":"1810.01266","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-generative-adversarial-imitation","title":"Improving Generative Adversarial Imitation Learning with Non-expert Demonstrations","date":"2018-09-27","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mimicking-actions-is-a-good-strategy-for","title":"Mimicking actions is a good strategy for beginners: Fast Reinforcement Learning with Expert Action Sequences","date":"2018-09-27","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-imitation-learning-with-recurrent-1","title":"Visual Imitation Learning with Recurrent Siamese Networks","date":"2018-09-27","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"what-would-pi-do-imitation-learning-via-off","title":"What Would pi* Do?: Imitation Learning via Off-Policy Reinforcement Learning","date":"2018-09-27","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"inspiration-learning-through-preferences","title":"Inspiration Learning through Preferences","date":"2018-09-16","arxiv_id":"1809.05872","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-ego-pose-estimation-via-imitation-learning","title":"3D Ego-Pose Estimation via Imitation Learning","date":"2018-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"shared-multi-task-imitation-learning-for","title":"Shared Multi-Task Imitation Learning for Indoor Self-Navigation","date":"2018-08-14","arxiv_id":"1808.04503","repositories_listed":0,"syntology":null},{"url":null,"slug":"risk-sensitive-generative-adversarial","title":"Risk-Sensitive Generative Adversarial Imitation Learning","date":"2018-08-13","arxiv_id":"1808.04468","repositories_listed":0,"syntology":null},{"url":null,"slug":"ensembledagger-a-bayesian-approach-to-safe","title":"EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning","date":"2018-07-22","arxiv_id":"1807.08364","repositories_listed":0,"syntology":null},{"url":null,"slug":"extracting-contact-and-motion-from","title":"Extracting Contact and Motion from Manipulation Videos","date":"2018-07-13","arxiv_id":"1807.04870","repositories_listed":0,"syntology":null},{"url":null,"slug":"cirl-controllable-imitative-reinforcement","title":"CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-driving","date":"2018-07-10","arxiv_id":"1807.03776","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-deep-imitation-learning-robot","title":"End-to-End Deep Imitation Learning: Robot Soccer Case Study","date":"2018-06-28","arxiv_id":"1807.09205","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-virtuous-machine-old-ethics-for-new","title":"The Virtuous Machine - Old Ethics for New Technology?","date":"2018-06-27","arxiv_id":"1806.10322","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-exploration-strategy-for-self","title":"Adversarial Active Exploration for Inverse Dynamics Model Learning","date":"2018-06-26","arxiv_id":"1806.10019","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-existing-social-conventions-in","title":"Learning Existing Social Conventions via Observationally Augmented Self-Play","date":"2018-06-26","arxiv_id":"1806.10071","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-neural-parsers-with-deterministic","title":"Learning Neural Parsers with Deterministic Differentiable Imitation Learning","date":"2018-06-20","arxiv_id":"1806.07822","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-imitation-learning","title":"Adaptive Input Estimation in Linear Dynamical Systems with Applications to Learning-from-Observations","date":"2018-06-19","arxiv_id":"1806.07200","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-policy-representations-in-multiagent","title":"Learning Policy Representations in Multiagent Systems","date":"2018-06-17","arxiv_id":"1806.06464","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-imitation-learning-with","title":"Accelerating Imitation Learning with Predictive Models","date":"2018-06-12","arxiv_id":"1806.04642","repositories_listed":0,"syntology":null},{"url":null,"slug":"agil-learning-attention-from-human-for","title":"AGIL: Learning Attention from Human for Visuomotor Tasks","date":"2018-06-01","arxiv_id":"1806.03960","repositories_listed":0,"syntology":null},{"url":null,"slug":"truncated-horizon-policy-search-combining","title":"Truncated Horizon Policy Search: Combining Reinforcement Learning & Imitation Learning","date":"2018-05-29","arxiv_id":"1805.11240","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-policy-learning-through-imitation-and","title":"Fast Policy Learning through Imitation and Reinforcement","date":"2018-05-26","arxiv_id":"1805.10413","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-self-imitating-diverse-policies","title":"Learning Self-Imitating Diverse Policies","date":"2018-05-25","arxiv_id":"1805.10309","repositories_listed":0,"syntology":null},{"url":null,"slug":"inverse-pomdp-inferring-what-you-think-from","title":"Inverse Rational Control: Inferring What You Think from How You Forage","date":"2018-05-24","arxiv_id":"1805.09864","repositories_listed":0,"syntology":null},{"url":null,"slug":"maximum-causal-tsallis-entropy-imitation","title":"Maximum Causal Tsallis Entropy Imitation Learning","date":"2018-05-22","arxiv_id":"1805.08336","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-driving-simulation-via-angle","title":"End-to-end driving simulation via angle branched network","date":"2018-05-19","arxiv_id":"1805.07545","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-temporal-strategic-relationships","title":"Learning Temporal Strategic Relationships using Generative Adversarial Imitation Learning","date":"2018-05-13","arxiv_id":"1805.04969","repositories_listed":0,"syntology":null},{"url":null,"slug":"event-extraction-with-generative-adversarial","title":"Event Extraction with Generative Adversarial Imitation Learning","date":"2018-04-21","arxiv_id":"1804.07881","repositories_listed":0,"syntology":null},{"url":null,"slug":"socially-guided-intrinsic-motivation-for","title":"Socially Guided Intrinsic Motivation for Robot Learning of Motor Skills","date":"2018-04-19","arxiv_id":"1804.07269","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-contracting-vector-fields-for-stable","title":"Learning Contracting Vector Fields For Stable Imitation Learning","date":"2018-04-13","arxiv_id":"1804.04878","repositories_listed":0,"syntology":null},{"url":null,"slug":"hindsight-is-only-5050-unsuitability-of-mdp","title":"Hindsight is Only 50/50: Unsuitability of MDP based Approximate POMDP Solvers for Multi-resolution Information Gathering","date":"2018-04-07","arxiv_id":"1804.02573","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-search-via-retrospective","title":"Learning to Search via Retrospective Imitation","date":"2018-04-03","arxiv_id":"1804.00846","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-end-to-end-imitation-learning-for-model","title":"Safe end-to-end imitation learning for model predictive control","date":"2018-03-27","arxiv_id":"1803.10231","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-learning-with-concurrent-actions-in","title":"Imitation Learning with Concurrent Actions in 3D Games","date":"2018-03-14","arxiv_id":"1803.05402","repositories_listed":0,"syntology":null},{"url":null,"slug":"oil-observational-imitation-learning","title":"OIL: Observational Imitation Learning","date":"2018-03-03","arxiv_id":"1803.01129","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-imitation-and-reinforcement","title":"Hierarchical Imitation and Reinforcement Learning","date":"2018-03-01","arxiv_id":"1803.00590","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-human-behaviors-in-crowds-by","title":"Understanding Human Behaviors in Crowds by Imitating the Decision-Making Process","date":"2018-01-25","arxiv_id":"1801.08391","repositories_listed":0,"syntology":null},{"url":null,"slug":"convergence-of-value-aggregation-for","title":"Convergence of Value Aggregation for Imitation Learning","date":"2018-01-22","arxiv_id":"1801.07292","repositories_listed":0,"syntology":null},{"url":null,"slug":"global-overview-of-imitation-learning","title":"Global overview of Imitation Learning","date":"2018-01-19","arxiv_id":"1801.06503","repositories_listed":0,"syntology":null},{"url":null,"slug":"deterministic-policy-imitation-gradient","title":"Deterministic Policy Imitation Gradient Algorithm","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"faster-reinforcement-learning-with-expert","title":"Faster Reinforcement Learning with Expert State Sequences","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-learning-from-visual-data-with","title":"Imitation Learning from Visual Data with Multiple Intentions","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-robust-rewards-with-adverserial","title":"Learning Robust Rewards with Adverserial Inverse Reinforcement Learning","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"model-based-imitation-learning-from-state","title":"Model-based imitation learning from state trajectories","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"parametrized-hierarchical-procedures-for","title":"Parametrized Hierarchical Procedures for Neural Programming","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-storytelling-via-generative","title":"Multimodal Storytelling via Generative Adversarial Imitation Learning","date":"2017-12-05","arxiv_id":"1712.01455","repositories_listed":0,"syntology":null},{"url":null,"slug":"state-aware-imitation-learning","title":"State Aware Imitation Learning","date":"2017-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deterministic-policy-optimization-by","title":"Deterministic Policy Optimization by Combining Pathwise and Score Function Estimators for Discrete Action Spaces","date":"2017-11-21","arxiv_id":"1711.08068","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-optimization-by-genetic-distillation","title":"Policy Optimization by Genetic Distillation","date":"2017-11-03","arxiv_id":"1711.01012","repositories_listed":0,"syntology":null},{"url":null,"slug":"burn-in-demonstrations-for-multi-modal","title":"Burn-In Demonstrations for Multi-Modal Imitation Learning","date":"2017-10-13","arxiv_id":"1710.05090","repositories_listed":0,"syntology":null},{"url":null,"slug":"predictive-state-decoders-encoding-the-future","title":"Predictive-State Decoders: Encoding the Future into Recurrent Networks","date":"2017-09-25","arxiv_id":"1709.08520","repositories_listed":0,"syntology":null},{"url":null,"slug":"avoidance-of-manual-labeling-in-robotic","title":"Avoidance of Manual Labeling in Robotic Autonomous Navigation Through Multi-Sensory Semi-Supervised Learning","date":"2017-09-22","arxiv_id":"1709.07911","repositories_listed":0,"syntology":null},{"url":null,"slug":"dropoutdagger-a-bayesian-approach-to-safe","title":"DropoutDAgger: A Bayesian Approach to Safe Imitation Learning","date":"2017-09-18","arxiv_id":"1709.06166","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-learning-for-vision-based-lane","title":"Imitation Learning for Vision-based Lane Keeping Assistance","date":"2017-09-12","arxiv_id":"1709.03853","repositories_listed":0,"syntology":null},{"url":null,"slug":"book-storing-algorithm-invariant-episodes-for","title":"BOOK: Storing Algorithm-Invariant Episodes for Deep Reinforcement Learning","date":"2017-09-05","arxiv_id":"1709.01308","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-whats-easy-fully-differentiable","title":"Learning What's Easy: Fully Differentiable Neural Easy-First Taggers","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"teaching-uavs-to-race-end-to-end-regression","title":"Teaching UAVs to Race: End-to-End Regression of Agile Controls in Simulation","date":"2017-08-19","arxiv_id":"1708.05884","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-differentiable-adversarial","title":"End-to-End Differentiable Adversarial Imitation Learning","date":"2017-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"local-bayesian-optimization-of-motor-skills","title":"Local Bayesian Optimization of Motor Skills","date":"2017-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-imitation-of-diverse-behaviors","title":"Robust Imitation of Diverse Behaviors","date":"2017-07-10","arxiv_id":"1707.02747","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-fast-integrated-planning-and-control","title":"A Fast Integrated Planning and Control Framework for Autonomous Driving via Imitation Learning","date":"2017-07-09","arxiv_id":"1707.02515","repositories_listed":0,"syntology":null},{"url":null,"slug":"path-integral-networks-end-to-end","title":"Path Integral Networks: End-to-End Differentiable Optimal Control","date":"2017-06-29","arxiv_id":"1706.09597","repositories_listed":0,"syntology":null},{"url":null,"slug":"energy-based-sequence-gans-for-recommendation","title":"Energy-Based Sequence GANs for Recommendation and Their Connection to Imitation Learning","date":"2017-06-28","arxiv_id":"1706.09200","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-learning-framework-for-automated-driving","title":"Meta learning Framework for Automated Driving","date":"2017-06-11","arxiv_id":"1706.04038","repositories_listed":0,"syntology":null},{"url":null,"slug":"visuospatial-skill-learning-for-robots","title":"Visuospatial Skill Learning for Robots","date":"2017-06-03","arxiv_id":"1706.00989","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-imitation-learning-from","title":"Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Nets","date":"2017-05-30","arxiv_id":"1705.10479","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-semantic-planning-using-deep-successor","title":"Visual Semantic Planning using Deep Successor Representations","date":"2017-05-23","arxiv_id":"1705.08080","repositories_listed":0,"syntology":null},{"url":null,"slug":"repeated-inverse-reinforcement-learning","title":"Repeated Inverse Reinforcement Learning","date":"2017-05-15","arxiv_id":"1705.05427","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-learning-for-structured-prediction","title":"Imitation learning for structured prediction in natural language processing","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"one-shot-imitation-learning","title":"One-Shot Imitation Learning","date":"2017-03-21","arxiv_id":"1703.07326","repositories_listed":0,"syntology":null},{"url":null,"slug":"coordinated-multi-agent-imitation-learning","title":"Coordinated Multi-Agent Imitation Learning","date":"2017-03-09","arxiv_id":"1703.03121","repositories_listed":0,"syntology":null},{"url":null,"slug":"deeply-aggrevated-differentiable-imitation","title":"Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction","date":"2017-03-03","arxiv_id":"1703.01030","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-hard-is-it-to-cross-the-room-training","title":"How hard is it to cross the room? -- Training (Recurrent) Neural Networks to steer a UAV","date":"2017-02-24","arxiv_id":"1702.07600","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-game-imitation-deep-supervised","title":"The Game Imitation: Deep Supervised Convolutional Networks for Quick Video Game AI","date":"2017-02-18","arxiv_id":"1702.05663","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-perceptual-rewards-for-imitation","title":"Unsupervised Perceptual Rewards for Imitation Learning","date":"2016-12-20","arxiv_id":"1612.06699","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-based-adversarial-imitation-learning","title":"Model-based Adversarial Imitation Learning","date":"2016-12-07","arxiv_id":"1612.02179","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-of-robotic-tasks-without-a","title":"Deep Learning of Robotic Tasks without a Simulator using Strong and Weak Human Supervision","date":"2016-12-04","arxiv_id":"1612.01086","repositories_listed":0,"syntology":null}],"record_sha256":"99e72fd26e74c24b81b34b178e5c8d299a90598c33d91cca8ddf7aaefc48fe81","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}