{"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/17","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":17,"pages_in_order":22,"rows_per_page":100,"rows":[1601,1700],"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/16","next":"/task/imitation-learning/papers/18","papers":[{"url":null,"slug":"reinforcement-learning-for-battery-energy","title":"Reinforcement Learning for Battery Energy Storage Dispatch augmented with Model-based Optimizer","date":"2021-09-02","arxiv_id":"2109.01659","repositories_listed":0,"syntology":null},{"url":null,"slug":"mimicbot-combining-imitation-and","title":"MimicBot: Combining Imitation and Reinforcement Learning to win in Bot Bowl","date":"2021-08-21","arxiv_id":"2108.09478","repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-efficient-generative-adversarial","title":"Provably Efficient Generative Adversarial Imitation Learning for Online and Offline Setting with Linear Function Approximation","date":"2021-08-19","arxiv_id":"2108.08765","repositories_listed":0,"syntology":null},{"url":null,"slug":"dq-gat-towards-safe-and-efficient-autonomous","title":"DQ-GAT: Towards Safe and Efficient Autonomous Driving with Deep Q-Learning and Graph Attention Networks","date":"2021-08-11","arxiv_id":"2108.05030","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-t-momentum-based-optimization-for","title":"Adaptive t-Momentum-based Optimization for Unknown Ratio of Outliers in Amateur Data in Imitation Learning","date":"2021-08-02","arxiv_id":"2108.00625","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-disentangled-representation-1","title":"Self-Supervised Disentangled Representation Learning for Third-Person Imitation Learning","date":"2021-08-02","arxiv_id":"2108.01069","repositories_listed":0,"syntology":null},{"url":null,"slug":"cluzh-at-sigmorphon-2021-shared-task-on","title":"CLUZH at SIGMORPHON 2021 Shared Task on Multilingual Grapheme-to-Phoneme Conversion: Variations on a Baseline","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generic-oracles-for-structured-prediction","title":"Generic Oracles for Structured Prediction","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-reinforcement-learning-for-mastering","title":"Meta-Reinforcement Learning for Mastering Multiple Skills and Generalizing across Environments in Text-based Games","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-deep-imitation-learning-for","title":"Transformer-based deep imitation learning for dual-arm robot manipulation","date":"2021-08-01","arxiv_id":"2108.00385","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforced-imitation-learning-by-free-energy","title":"Reinforced Imitation Learning by Free Energy Principle","date":"2021-07-25","arxiv_id":"2107.11811","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-electric-vehicle-charging","title":"Training Electric Vehicle Charging Controllers with Imitation Learning","date":"2021-07-21","arxiv_id":"2107.10111","repositories_listed":0,"syntology":null},{"url":null,"slug":"playful-interactions-for-representation","title":"Playful Interactions for Representation Learning","date":"2021-07-19","arxiv_id":"2107.09046","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitate-theworld-a-search-engine-simulation","title":"Imitate TheWorld: A Search Engine Simulation Platform","date":"2021-07-16","arxiv_id":"2107.07693","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-adversarial-imitation-learning-using","title":"Visual Adversarial Imitation Learning using Variational Models","date":"2021-07-16","arxiv_id":"2107.08829","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-stable-molecules-using-imitation","title":"Generating stable molecules using imitation and reinforcement learning","date":"2021-07-11","arxiv_id":"2107.05007","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-imitation-learning-with-copulas-1","title":"Multi-Agent Imitation Learning with Copulas","date":"2021-07-10","arxiv_id":"2107.04750","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-by-predicting-observations","title":"Imitation by Predicting Observations","date":"2021-07-08","arxiv_id":"2107.03851","repositories_listed":0,"syntology":null},{"url":"/paper/the-minerl-basalt-competition-on-learning","slug":"the-minerl-basalt-competition-on-learning","title":"The MineRL BASALT Competition on Learning from Human Feedback","date":"2021-07-05","arxiv_id":"2107.01969","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-generative-adversarial-imitation","title":"On the Benefits of Inducing Local Lipschitzness for Robust Generative Adversarial Imitation Learning","date":"2021-06-30","arxiv_id":"2107.00116","repositories_listed":0,"syntology":null},{"url":null,"slug":"expert-q-learning-deep-q-learning-with-state","title":"Expert Q-learning: Deep Reinforcement Learning with Coarse State Values from Offline Expert Examples","date":"2021-06-28","arxiv_id":"2106.14642","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-sequential-recommendation","title":"Improving Sequential Recommendation Consistency with Self-Supervised Imitation","date":"2021-06-26","arxiv_id":"2106.14031","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-the-spread-of-covid-19-epidemic","title":"Understanding the Spread of COVID-19 Epidemic: A Spatio-Temporal Point Process View","date":"2021-06-24","arxiv_id":"2106.13097","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-learning-progress-taxonomies-and","title":"Imitation Learning: Progress, Taxonomies and Challenges","date":"2021-06-23","arxiv_id":"2106.12177","repositories_listed":0,"syntology":null},{"url":null,"slug":"nearly-minimax-optimal-adversarial-imitation","title":"On Generalization of Adversarial Imitation Learning and Beyond","date":"2021-06-19","arxiv_id":"2106.10424","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-differently-acting-similarly-imitation","title":"Seeing Differently, Acting Similarly: Heterogeneously Observable Imitation Learning","date":"2021-06-17","arxiv_id":"2106.09256","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-curricula-via-expert-demonstrations","title":"Automatic Curricula via Expert Demonstrations","date":"2021-06-16","arxiv_id":"2106.09159","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparsedice-imitation-learning-for-temporally","title":"SparseDice: Imitation Learning for Temporally Sparse Data via Regularization","date":"2021-06-13","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"keyframe-focused-visual-imitation-learning","title":"Keyframe-Focused Visual Imitation Learning","date":"2021-06-11","arxiv_id":"2106.06452","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-gradient-bayesian-robust-optimization","title":"Policy Gradient Bayesian Robust Optimization for Imitation Learning","date":"2021-06-11","arxiv_id":"2106.06499","repositories_listed":0,"syntology":null},{"url":null,"slug":"differentiable-robust-lqr-layers","title":"Differentiable Robust LQR Layers","date":"2021-06-10","arxiv_id":"2106.05535","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-inverse-reinforcement-learning","title":"Offline Inverse Reinforcement Learning","date":"2021-06-09","arxiv_id":"2106.05068","repositories_listed":0,"syntology":null},{"url":null,"slug":"concave-utility-reinforcement-learning-the","title":"Concave Utility Reinforcement Learning: the Mean-Field Game Viewpoint","date":"2021-06-07","arxiv_id":"2106.03787","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-without-knowing-unobserved-context","title":"Learning without Knowing: Unobserved Context in Continuous Transfer Reinforcement Learning","date":"2021-06-07","arxiv_id":"2106.03833","repositories_listed":0,"syntology":null},{"url":null,"slug":"softdice-for-imitation-learning-rethinking","title":"SoftDICE for Imitation Learning: Rethinking Off-policy Distribution Matching","date":"2021-06-06","arxiv_id":"2106.03155","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-task-adaptation-using-natural","title":"Zero-shot Task Adaptation using Natural Language","date":"2021-06-05","arxiv_id":"2106.02972","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-adversarial-imitation-learning-for","title":"Generative Adversarial Imitation Learning for Empathy-based AI","date":"2021-05-27","arxiv_id":"2105.13328","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-navigation-for-racing-drones-based-on","title":"Robust Navigation for Racing Drones based on Imitation Learning and Modularization","date":"2021-05-27","arxiv_id":"2105.12923","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-data-do-we-need-for-training-an-av","title":"What data do we need for training an AV motion planner?","date":"2021-05-26","arxiv_id":"2105.12337","repositories_listed":0,"syntology":null},{"url":null,"slug":"hyperparameter-selection-for-imitation","title":"Hyperparameter Selection for Imitation Learning","date":"2021-05-25","arxiv_id":"2105.12034","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-understanding-for-field-and-service","title":"Language Understanding for Field and Service Robots in a Priori Unknown Environments","date":"2021-05-21","arxiv_id":"2105.10396","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-domain-imitation-from-observations","title":"Cross-domain Imitation from Observations","date":"2021-05-20","arxiv_id":"2105.10037","repositories_listed":0,"syntology":null},{"url":null,"slug":"voila-visual-observation-only-imitation","title":"VOILA: Visual-Observation-Only Imitation Learning for Autonomous Navigation","date":"2021-05-19","arxiv_id":"2105.09371","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-hierarchical-imitation-learning","title":"Explainable Hierarchical Imitation Learning for Robotic Drink Pouring","date":"2021-05-16","arxiv_id":"2105.07348","repositories_listed":0,"syntology":null},{"url":null,"slug":"make-bipedal-robots-learn-how-to-imitate","title":"Make Bipedal Robots Learn How to Imitate","date":"2021-05-15","arxiv_id":"2105.07193","repositories_listed":0,"syntology":null},{"url":null,"slug":"coarse-to-fine-imitation-learning-robot","title":"Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstration","date":"2021-05-13","arxiv_id":"2105.06411","repositories_listed":0,"syntology":null},{"url":null,"slug":"rail-a-modular-framework-for-reinforcement","title":"RAIL: A modular framework for Reinforcement-learning-based Adversarial Imitation Learning","date":"2021-05-08","arxiv_id":"2105.03756","repositories_listed":0,"syntology":null},{"url":null,"slug":"code-collocation-for-demonstration-encoding","title":"Imitation Learning via Simultaneous Optimization of Policies and Auxiliary Trajectories","date":"2021-05-07","arxiv_id":"2105.03019","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-algorithms-for-regenerative-stopping","title":"Learning Algorithms for Regenerative Stopping Problems with Applications to Shipping Consolidation in Logistics","date":"2021-05-05","arxiv_id":"2105.02318","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-lottery-tickets-and-minimal-task","title":"On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning","date":"2021-05-04","arxiv_id":"2105.01648","repositories_listed":0,"syntology":null},{"url":null,"slug":"h2o-a-benchmark-for-visual-human-human-object","title":"H2O: A Benchmark for Visual Human-human Object Handover Analysis","date":"2021-04-23","arxiv_id":"2104.11466","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-learning-with-attention-for-end-to","title":"Multi-task Learning with Attention for End-to-end Autonomous Driving","date":"2021-04-21","arxiv_id":"2104.10753","repositories_listed":0,"syntology":null},{"url":null,"slug":"skeletal-feature-compensation-for-imitation","title":"Skeletal Feature Compensation for Imitation Learning with Embodiment Mismatch","date":"2021-04-15","arxiv_id":"2104.07810","repositories_listed":0,"syntology":null},{"url":null,"slug":"gan-based-interactive-reinforcement-learning","title":"GAN-Based Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback","date":"2021-04-14","arxiv_id":"2104.06600","repositories_listed":0,"syntology":null},{"url":null,"slug":"reward-function-shape-exploration-in","title":"Reward function shape exploration in adversarial imitation learning: an empirical study","date":"2021-04-14","arxiv_id":"2104.06687","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-simulation-of-ride-hailing","title":"Data-Driven Simulation of Ride-Hailing Services using Imitation and Reinforcement Learning","date":"2021-04-06","arxiv_id":"2104.02661","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-online-from-corrective-feedback-a","title":"Learning Online from Corrective Feedback: A Meta-Algorithm for Robotics","date":"2021-04-02","arxiv_id":"2104.01021","repositories_listed":0,"syntology":null},{"url":null,"slug":"uav-assisted-communication-in-remote-disaster","title":"UAV-Assisted Communication in Remote Disaster Areas using Imitation Learning","date":"2021-04-02","arxiv_id":"2105.12823","repositories_listed":0,"syntology":null},{"url":null,"slug":"dealio-data-efficient-adversarial-learning","title":"DEALIO: Data-Efficient Adversarial Learning for Imitation from Observation","date":"2021-03-31","arxiv_id":"2104.00163","repositories_listed":0,"syntology":null},{"url":null,"slug":"lazydagger-reducing-context-switching-in","title":"LazyDAgger: Reducing Context Switching in Interactive Imitation Learning","date":"2021-03-31","arxiv_id":"2104.00053","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-robust-feedback-policies-from","title":"Learning Lipschitz Feedback Policies from Expert Demonstrations: Closed-Loop Guarantees, Generalization and Robustness","date":"2021-03-30","arxiv_id":"2103.16629","repositories_listed":0,"syntology":null},{"url":null,"slug":"co-imitation-learning-without-expert","title":"Co-Imitation Learning without Expert Demonstration","date":"2021-03-27","arxiv_id":"2103.14823","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-learning-from-mpc-for-quadrupedal","title":"Imitation Learning from MPC for Quadrupedal Multi-Gait Control","date":"2021-03-26","arxiv_id":"2103.14331","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-imitation-learning-by-planning","title":"Self-Imitation Learning by Planning","date":"2021-03-25","arxiv_id":"2103.13834","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-imitation-learning-of-linear-control","title":"On Imitation Learning of Linear Control Policies: Enforcing Stability and Robustness Constraints via LMI Conditions","date":"2021-03-24","arxiv_id":"2103.12945","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-6dof-grasping-using-reward","title":"Learning 6DoF Grasping Using Reward-Consistent Demonstration","date":"2021-03-23","arxiv_id":"2103.12321","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-adaptable-policy-via-meta","title":"Meta-Adversarial Inverse Reinforcement Learning for Decision-making Tasks","date":"2021-03-23","arxiv_id":"2103.12694","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-offline-reinforcement-learning-and","title":"Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism","date":"2021-03-22","arxiv_id":"2103.12021","repositories_listed":0,"syntology":null},{"url":null,"slug":"introspective-visuomotor-control-exploiting","title":"Introspective Visuomotor Control: Exploiting Uncertainty in Deep Visuomotor Control for Failure Recovery","date":"2021-03-22","arxiv_id":"2103.11881","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-simulate-on-sparse-trajectory","title":"Learning to Simulate on Sparse Trajectory Data","date":"2021-03-22","arxiv_id":"2103.11845","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimism-is-all-you-need-model-based-1","title":"Optimism is All You Need: Model-Based Imitation Learning From Observation Alone","date":"2021-03-09","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"variational-model-based-imitation-learning-in","title":"Variational Model-Based Imitation Learning in High-Dimensional Observation Spaces","date":"2021-03-09","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-monopoly-gameplay-a-hybrid-model","title":"Decision Making in Monopoly using a Hybrid Deep Reinforcement Learning Approach","date":"2021-03-01","arxiv_id":"2103.00683","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalization-through-hand-eye-coordination","title":"Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Control","date":"2021-02-28","arxiv_id":"2103.00375","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-and-interpretable-robot","title":"Efficient and Interpretable Robot Manipulation with Graph Neural Networks","date":"2021-02-25","arxiv_id":"2102.13177","repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-learning-for-robust-and-safe-real","title":"Learning-based Robust Motion Planning with Guaranteed Stability: A Contraction Theory Approach","date":"2021-02-25","arxiv_id":"2102.12668","repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-breaking-the-quadratic-error","title":"Provably Breaking the Quadratic Error Compounding Barrier in Imitation Learning, Optimally","date":"2021-02-25","arxiv_id":"2102.12948","repositories_listed":0,"syntology":null},{"url":null,"slug":"closing-the-closed-loop-distribution-shift-in","title":"On the Sample Complexity of Stability Constrained Imitation Learning","date":"2021-02-18","arxiv_id":"2102.09161","repositories_listed":0,"syntology":null},{"url":null,"slug":"fully-general-online-imitation-learning","title":"Fully General Online Imitation Learning","date":"2021-02-17","arxiv_id":"2102.08686","repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-matters-offline-pretraining","title":"Representation Matters: Offline Pretraining for Sequential Decision Making","date":"2021-02-11","arxiv_id":"2102.05815","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-equational-theorem-proving","title":"Learning Equational Theorem Proving","date":"2021-02-10","arxiv_id":"2102.05547","repositories_listed":0,"syntology":null},{"url":null,"slug":"feedback-in-imitation-learning-confusion-on","title":"Feedback in Imitation Learning: The Three Regimes of Covariate Shift","date":"2021-02-04","arxiv_id":"2102.02872","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-adversarial-inverse-reinforcement","title":"Hybrid Adversarial Imitation Learning","date":"2021-02-04","arxiv_id":"2102.02454","repositories_listed":0,"syntology":null},{"url":null,"slug":"gaze-based-dual-resolution-deep-imitation","title":"Gaze-based dual resolution deep imitation learning for high-precision dexterous robot manipulation","date":"2021-02-02","arxiv_id":"2102.01295","repositories_listed":0,"syntology":null},{"url":null,"slug":"autonomous-navigation-through-intersections","title":"Autonomous Navigation through intersections with Graph ConvolutionalNetworks and Conditional Imitation Learning for Self-driving Cars","date":"2021-02-01","arxiv_id":"2102.00675","repositories_listed":0,"syntology":null},{"url":null,"slug":"embedding-symbolic-temporal-knowledge-into","title":"Embedding Symbolic Temporal Knowledge into Deep Sequential Models","date":"2021-01-28","arxiv_id":"2101.11981","repositories_listed":0,"syntology":null},{"url":null,"slug":"ec-sagins-edge-computing-enhanced-space-air","title":"EC-SAGINs: Edge Computing-enhanced Space-Air-Ground Integrated Networks for Internet of Vehicles","date":"2021-01-15","arxiv_id":"2101.06056","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-synthetic-characters-for-military","title":"Adaptive Synthetic Characters for Military Training","date":"2021-01-06","arxiv_id":"2101.02185","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-maximum-entropy-behavior-cloning","title":"Robust Maximum Entropy Behavior Cloning","date":"2021-01-04","arxiv_id":"2101.01251","repositories_listed":0,"syntology":null},{"url":null,"slug":"sda-improving-text-generation-with-self-data","title":"SDA: Improving Text Generation with Self Data Augmentation","date":"2021-01-02","arxiv_id":"2101.03236","repositories_listed":0,"syntology":null},{"url":null,"slug":"behavioral-cloning-from-noisy-demonstrations","title":"Behavioral Cloning from Noisy Demonstrations","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cag-qil-context-aware-actionness-grouping-via","title":"CAG-QIL: Context-Aware Actionness Grouping via Q Imitation Learning for Online Temporal Action Localization","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-imitation-and-reinforcement","title":"Combining Imitation and Reinforcement Learning with Free Energy Principle","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"goal-driven-imitation-learning-from","title":"Goal-Driven Imitation Learning from Observation by Inferring Goal Proximity","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-efficient-planning-based-rewards-for","title":"Learning Efficient Planning-based Rewards for Imitation Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-from-demonstrations-with-energy","title":"Learning from Demonstrations with Energy based Generative Adversarial Imitation Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-task-decomposition-with-order-memory","title":"Learning Task Decomposition with Order-Memory Policy Network","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-make-decisions-via-submodular","title":"Learning to Make Decisions via Submodular Regularization","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-search-for-fast-maximum-common","title":"Learning to Search for Fast Maximum Common Subgraph Detection","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"peril-probabilistic-embeddings-for-hybrid","title":"PERIL: Probabilistic Embeddings for hybrid Meta-Reinforcement and Imitation Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"1e70ec584a507e059f0fb8cc6f3cf7ed3e87bd6e5a0165f2a008e76126c63137","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}