{"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/4","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":4,"pages_in_order":22,"rows_per_page":100,"rows":[301,400],"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/3","next":"/task/imitation-learning/papers/5","papers":[{"url":"/paper/embodied-multi-modal-agent-trained-by-an-llm","slug":"embodied-multi-modal-agent-trained-by-an-llm","title":"Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld","date":"2023-11-28","arxiv_id":"2311.16714","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":10,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/embodied-multi-modal-agent-trained-by-an-llm#ran","syntology_url":"https://syntology.ai/paper/2311.16714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.16714"}},"official":{"repos":["stevenyangyj/emma-alfworld"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/beyond-imitation-leveraging-fine-grained","slug":"beyond-imitation-leveraging-fine-grained","title":"Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment","date":"2023-11-07","arxiv_id":"2311.04072","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/beyond-imitation-leveraging-fine-grained#ran","syntology_url":"https://syntology.ai/paper/2311.04072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.04072"}},"official":{"repos":["rucaibox/figa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/push-it-to-the-demonstrated-limit-multimodal","slug":"push-it-to-the-demonstrated-limit-multimodal","title":"Multimodal and Force-Matched Imitation Learning with a See-Through Visuotactile Sensor","date":"2023-11-02","arxiv_id":"2311.01248","repositories_listed":1,"syntology":null},{"url":"/paper/letfuser-light-weight-end-to-end-transformer","slug":"letfuser-light-weight-end-to-end-transformer","title":"LeTFuser: Light-weight End-to-end Transformer-Based Sensor Fusion for Autonomous Driving with Multi-Task Learning","date":"2023-10-19","arxiv_id":"2310.13135","repositories_listed":1,"syntology":null},{"url":"/paper/towards-example-based-nmt-with-multi","slug":"towards-example-based-nmt-with-multi","title":"Towards Example-Based NMT with Multi-Levenshtein Transformers","date":"2023-10-13","arxiv_id":"2310.08967","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":1,"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/towards-example-based-nmt-with-multi#ran","syntology_url":"https://syntology.ai/paper/2310.08967","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.08967"}},"official":{"repos":["maxwell1447/fairseq"],"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/imitation-learning-from-observation-with","slug":"imitation-learning-from-observation-with","title":"Imitation Learning from Observation with Automatic Discount Scheduling","date":"2023-10-11","arxiv_id":"2310.07433","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":1,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":4,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/imitation-learning-from-observation-with#ran","syntology_url":"https://syntology.ai/paper/2310.07433","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07433"}},"official":null}},{"url":"/paper/imitation-learning-from-purified","slug":"imitation-learning-from-purified","title":"Imitation Learning from Purified Demonstrations","date":"2023-10-11","arxiv_id":"2310.07143","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/imitation-learning-from-purified#ran","syntology_url":"https://syntology.ai/paper/2310.07143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07143"}},"official":{"repos":["yunke-wang/dp-il"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/roboclip-one-demonstration-is-enough-to-learn","slug":"roboclip-one-demonstration-is-enough-to-learn","title":"RoboCLIP: One Demonstration is Enough to Learn Robot Policies","date":"2023-10-11","arxiv_id":"2310.07899","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/roboclip-one-demonstration-is-enough-to-learn#ran","syntology_url":"https://syntology.ai/paper/2310.07899","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07899"}},"official":null}},{"url":"/paper/offline-imitation-learning-with-variational","slug":"offline-imitation-learning-with-variational","title":"Offline Imitation Learning with Variational Counterfactual Reasoning","date":"2023-10-07","arxiv_id":"2310.04706","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-imitation-learning-from-visual","slug":"adversarial-imitation-learning-from-visual","title":"Adversarial Imitation Learning from Visual Observations using Latent Information","date":"2023-09-29","arxiv_id":"2309.17371","repositories_listed":1,"syntology":null},{"url":"/paper/tora-a-tool-integrated-reasoning-agent-for","slug":"tora-a-tool-integrated-reasoning-agent-for","title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","date":"2023-09-29","arxiv_id":"2309.17452","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":9,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tora-a-tool-integrated-reasoning-agent-for#ran","syntology_url":"https://syntology.ai/paper/2309.17452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17452"}},"official":{"repos":["microsoft/tora"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-reinforcement-learning-approach-for-robotic","slug":"a-reinforcement-learning-approach-for-robotic","title":"A Reinforcement Learning Approach for Robotic Unloading from Visual Observations","date":"2023-09-12","arxiv_id":"2309.06621","repositories_listed":1,"syntology":null},{"url":"/paper/everyone-deserves-a-reward-learning","slug":"everyone-deserves-a-reward-learning","title":"Everyone Deserves A Reward: Learning Customized Human Preferences","date":"2023-09-06","arxiv_id":"2309.03126","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/everyone-deserves-a-reward-learning#ran","syntology_url":"https://syntology.ai/paper/2309.03126","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.03126"}},"official":{"repos":["linear95/dsp"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-robot-learning-through-learned","slug":"enhancing-robot-learning-through-learned","title":"Enhancing Robot Learning through Learned Human-Attention Feature Maps","date":"2023-08-29","arxiv_id":"2308.15327","repositories_listed":1,"syntology":null},{"url":"/paper/bridgedata-v2-a-dataset-for-robot-learning-at","slug":"bridgedata-v2-a-dataset-for-robot-learning-at","title":"BridgeData V2: A Dataset for Robot Learning at Scale","date":"2023-08-24","arxiv_id":"2308.12952","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/bridgedata-v2-a-dataset-for-robot-learning-at#ran","syntology_url":"https://syntology.ai/paper/2308.12952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12952"}},"official":{"repos":["rail-berkeley/BridgeData-V2"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/small-object-detection-via-coarse-to-fine","slug":"small-object-detection-via-coarse-to-fine","title":"Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning","date":"2023-08-18","arxiv_id":"2308.09534","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/small-object-detection-via-coarse-to-fine#ran","syntology_url":"https://syntology.ai/paper/2308.09534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09534"}},"official":{"repos":["shaunyuan22/cfinet"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/semantics-guided-transformer-based-sensor","slug":"semantics-guided-transformer-based-sensor","title":"Cognitive TransFuser: Semantics-guided Transformer-based Sensor Fusion for Improved Waypoint Prediction","date":"2023-08-04","arxiv_id":"2308.02126","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-data-generation-in-vision-and","slug":"scaling-data-generation-in-vision-and","title":"Scaling Data Generation in Vision-and-Language Navigation","date":"2023-07-28","arxiv_id":"2307.15644","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/scaling-data-generation-in-vision-and#ran","syntology_url":"https://syntology.ai/paper/2307.15644","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.15644"}},"official":{"repos":["wz0919/scalevln"],"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/deep-homography-prediction-for-endoscopic","slug":"deep-homography-prediction-for-endoscopic","title":"Deep Homography Prediction for Endoscopic Camera Motion Imitation Learning","date":"2023-07-24","arxiv_id":"2307.12792","repositories_listed":1,"syntology":null},{"url":"/paper/xskill-cross-embodiment-skill-discovery","slug":"xskill-cross-embodiment-skill-discovery","title":"XSkill: Cross Embodiment Skill Discovery","date":"2023-07-19","arxiv_id":"2307.09955","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/xskill-cross-embodiment-skill-discovery#ran","syntology_url":"https://syntology.ai/paper/2307.09955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09955"}},"official":{"repos":["real-stanford/xskill"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-laws-for-imitation-learning-in","slug":"scaling-laws-for-imitation-learning-in","title":"Scaling Laws for Imitation Learning in Single-Agent Games","date":"2023-07-18","arxiv_id":"2307.09423","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scaling-laws-for-imitation-learning-in#ran","syntology_url":"https://syntology.ai/paper/2307.09423","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09423"}},"official":{"repos":["princeton-nlp/il-scaling-in-games"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-end-to-end-speech-translation-by-2","slug":"improving-end-to-end-speech-translation-by-2","title":"Improving End-to-End Speech Translation by Imitation-Based Knowledge Distillation with Synthetic Transcripts","date":"2023-07-17","arxiv_id":"2307.08426","repositories_listed":1,"syntology":null},{"url":"/paper/iifl-implicit-interactive-fleet-learning-from","slug":"iifl-implicit-interactive-fleet-learning-from","title":"IIFL: Implicit Interactive Fleet Learning from Heterogeneous Human Supervisors","date":"2023-06-27","arxiv_id":"2306.15228","repositories_listed":1,"syntology":null},{"url":"/paper/learning-non-markovian-decision-making-from","slug":"learning-non-markovian-decision-making-from","title":"Learning non-Markovian Decision-Making from State-only Sequences","date":"2023-06-27","arxiv_id":"2306.15156","repositories_listed":1,"syntology":null},{"url":"/paper/reasoning-over-the-air-a-reasoning-based","slug":"reasoning-over-the-air-a-reasoning-based","title":"Reasoning over the Air: A Reasoning-based Implicit Semantic-Aware Communication Framework","date":"2023-06-20","arxiv_id":"2306.11229","repositories_listed":1,"syntology":null},{"url":"/paper/active-policy-improvement-from-multiple-black","slug":"active-policy-improvement-from-multiple-black","title":"Active Policy Improvement from Multiple Black-box Oracles","date":"2023-06-17","arxiv_id":"2306.10259","repositories_listed":1,"syntology":null},{"url":"/paper/sample-efficient-on-policy-imitation-learning","slug":"sample-efficient-on-policy-imitation-learning","title":"Mimicking Better by Matching the Approximate Action Distribution","date":"2023-06-16","arxiv_id":"2306.09805","repositories_listed":1,"syntology":null},{"url":"/paper/seeing-the-pose-in-the-pixels-learning-pose","slug":"seeing-the-pose-in-the-pixels-learning-pose","title":"Seeing the Pose in the Pixels: Learning Pose-Aware Representations in Vision Transformers","date":"2023-06-15","arxiv_id":"2306.09331","repositories_listed":1,"syntology":null},{"url":"/paper/curricular-subgoals-for-inverse-reinforcement","slug":"curricular-subgoals-for-inverse-reinforcement","title":"Curricular Subgoals for Inverse Reinforcement Learning","date":"2023-06-14","arxiv_id":"2306.08232","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-stabilize-high-dimensional","slug":"learning-to-stabilize-high-dimensional","title":"Learning to Stabilize High-dimensional Unknown Systems Using Lyapunov-guided Exploration","date":"2023-06-14","arxiv_id":"2306.08722","repositories_listed":1,"syntology":null},{"url":"/paper/skill-disentanglement-for-imitation-learning","slug":"skill-disentanglement-for-imitation-learning","title":"Skill Disentanglement for Imitation Learning from Suboptimal Demonstrations","date":"2023-06-13","arxiv_id":"2306.07919","repositories_listed":1,"syntology":null},{"url":"/paper/provably-efficient-adversarial-imitation","slug":"provably-efficient-adversarial-imitation","title":"Provably Efficient Adversarial Imitation Learning with Unknown Transitions","date":"2023-06-11","arxiv_id":"2306.06563","repositories_listed":1,"syntology":null},{"url":"/paper/liv-language-image-representations-and","slug":"liv-language-image-representations-and","title":"LIV: Language-Image Representations and Rewards for Robotic Control","date":"2023-06-01","arxiv_id":"2306.00958","repositories_listed":1,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/liv-language-image-representations-and#ran","syntology_url":"https://syntology.ai/paper/2306.00958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00958"}},"official":{"repos":["penn-pal-lab/liv"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/thought-cloning-learning-to-think-while-1","slug":"thought-cloning-learning-to-think-while-1","title":"Thought Cloning: Learning to Think while Acting by Imitating Human Thinking","date":"2023-06-01","arxiv_id":"2306.00323","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/thought-cloning-learning-to-think-while-1#ran","syntology_url":"https://syntology.ai/paper/2306.00323","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00323"}},"official":{"repos":["ShengranHu/Thought-Cloning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/what-is-essential-for-unseen-goal","slug":"what-is-essential-for-unseen-goal","title":"What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?","date":"2023-05-30","arxiv_id":"2305.18882","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/what-is-essential-for-unseen-goal#ran","syntology_url":"https://syntology.ai/paper/2305.18882","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18882"}},"official":{"repos":["yangrui2015/goat"],"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/neural-task-synthesis-for-visual-programming","slug":"neural-task-synthesis-for-visual-programming","title":"Neural Task Synthesis for Visual Programming","date":"2023-05-26","arxiv_id":"2305.18342","repositories_listed":1,"syntology":null},{"url":"/paper/coherent-soft-imitation-learning","slug":"coherent-soft-imitation-learning","title":"Coherent Soft Imitation Learning","date":"2023-05-25","arxiv_id":"2305.16498","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/coherent-soft-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/2305.16498","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16498"}},"official":{"repos":["google-deepmind/csil"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/2305-14550","slug":"2305-14550","title":"When should we prefer Decision Transformers for Offline Reinforcement Learning?","date":"2023-05-23","arxiv_id":"2305.14550","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 2 unverified","sample_list":"/paper/2305-14550#ran","syntology_url":"https://syntology.ai/paper/2305.14550","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14550"}},"official":{"repos":["prajjwal1/rl_paradigm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/learn-from-mistakes-through-cooperative","slug":"learn-from-mistakes-through-cooperative","title":"Learning from Mistakes via Cooperative Study Assistant for Large Language Models","date":"2023-05-23","arxiv_id":"2305.13829","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learn-from-mistakes-through-cooperative#ran","syntology_url":"https://syntology.ai/paper/2305.13829","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13829"}},"official":{"repos":["dqwang122/salam"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/furniturebench-reproducible-real-world","slug":"furniturebench-reproducible-real-world","title":"FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulation","date":"2023-05-22","arxiv_id":"2305.12821","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/furniturebench-reproducible-real-world#ran","syntology_url":"https://syntology.ai/paper/2305.12821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.12821"}},"official":{"repos":["clvrai/furniture-bench"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-task-hierarchical-adversarial-inverse","slug":"multi-task-hierarchical-adversarial-inverse","title":"Multi-task Hierarchical Adversarial Inverse Reinforcement Learning","date":"2023-05-22","arxiv_id":"2305.12633","repositories_listed":1,"syntology":null},{"url":"/paper/distance-weighted-supervised-learning-for","slug":"distance-weighted-supervised-learning-for","title":"Distance Weighted Supervised Learning for Offline Interaction Data","date":"2023-04-26","arxiv_id":"2304.13774","repositories_listed":1,"syntology":{"n":27,"n_ran":14,"n_constructed":0,"n_ran_checked":4,"n_instrument":10,"n_unverified":13,"n_honours":2,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/distance-weighted-supervised-learning-for#ran","syntology_url":"https://syntology.ai/paper/2304.13774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.13774"}},"official":null}},{"url":"/paper/learning-representative-trajectories-of","slug":"learning-representative-trajectories-of","title":"Learning Representative Trajectories of Dynamical Systems via Domain-Adaptive Imitation","date":"2023-04-19","arxiv_id":"2304.10260","repositories_listed":1,"syntology":null},{"url":"/paper/using-offline-data-to-speed-up-reinforcement","slug":"using-offline-data-to-speed-up-reinforcement","title":"Using Offline Data to Speed Up Reinforcement Learning in Procedurally Generated Environments","date":"2023-04-18","arxiv_id":"2304.09825","repositories_listed":1,"syntology":null},{"url":"/paper/curriculum-based-imitation-of-versatile","slug":"curriculum-based-imitation-of-versatile","title":"Curriculum-Based Imitation of Versatile Skills","date":"2023-04-11","arxiv_id":"2304.05171","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-action-space-mismatch-in-learning","slug":"bridging-action-space-mismatch-in-learning","title":"Learning Robot Manipulation from Cross-Morphology Demonstration","date":"2023-04-07","arxiv_id":"2304.03833","repositories_listed":1,"syntology":null},{"url":"/paper/goal-conditioned-imitation-learning-using","slug":"goal-conditioned-imitation-learning-using","title":"Goal-Conditioned Imitation Learning using Score-based Diffusion Policies","date":"2023-04-05","arxiv_id":"2304.02532","repositories_listed":1,"syntology":null},{"url":"/paper/chain-of-thought-predictive-control","slug":"chain-of-thought-predictive-control","title":"Chain-of-Thought Predictive Control","date":"2023-04-03","arxiv_id":"2304.00776","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 1 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) · 4 unverified","sample_list":"/paper/chain-of-thought-predictive-control#ran","syntology_url":"https://syntology.ai/paper/2304.00776","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.00776"}},"official":{"repos":["seanjia/cotpc"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/generative-adversarial-neuroevolution-for","slug":"generative-adversarial-neuroevolution-for","title":"Generative Adversarial Neuroevolution for Control Behaviour Imitation","date":"2023-04-03","arxiv_id":"2304.12432","repositories_listed":1,"syntology":null},{"url":"/paper/mahalo-unifying-offline-reinforcement","slug":"mahalo-unifying-offline-reinforcement","title":"MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from Observations","date":"2023-03-30","arxiv_id":"2303.17156","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/mahalo-unifying-offline-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2303.17156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17156"}},"official":{"repos":["anqili/mahalo"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/probabilistic-inverse-optimal-control-for-non","slug":"probabilistic-inverse-optimal-control-for-non","title":"Probabilistic inverse optimal control for non-linear partially observable systems disentangles perceptual uncertainty and behavioral costs","date":"2023-03-29","arxiv_id":"2303.16698","repositories_listed":1,"syntology":null},{"url":"/paper/improving-code-generation-by-training-with","slug":"improving-code-generation-by-training-with","title":"Improving Code Generation by Training with Natural Language Feedback","date":"2023-03-28","arxiv_id":"2303.16749","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":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) · 0 unverified","sample_list":"/paper/improving-code-generation-by-training-with#ran","syntology_url":"https://syntology.ai/paper/2303.16749","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16749"}},"official":{"repos":["nyu-mll/ILF-for-code-generation"],"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/training-language-models-with-language","slug":"training-language-models-with-language","title":"Training Language Models with Language Feedback at Scale","date":"2023-03-28","arxiv_id":"2303.16755","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/training-language-models-with-language#ran","syntology_url":"https://syntology.ai/paper/2303.16755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16755"}},"official":{"repos":["jeremyalain/imitation_learning_from_language_feedback"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/information-maximizing-curriculum-a","slug":"information-maximizing-curriculum-a","title":"Information Maximizing Curriculum: A Curriculum-Based Approach for Imitating Diverse Skills","date":"2023-03-27","arxiv_id":"2303.15349","repositories_listed":1,"syntology":null},{"url":"/paper/inverse-reinforcement-learning-without","slug":"inverse-reinforcement-learning-without","title":"Inverse Reinforcement Learning without Reinforcement Learning","date":"2023-03-26","arxiv_id":"2303.14623","repositories_listed":1,"syntology":null},{"url":"/paper/optimal-transport-for-offline-imitation","slug":"optimal-transport-for-offline-imitation","title":"Optimal Transport for Offline Imitation Learning","date":"2023-03-24","arxiv_id":"2303.13971","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/optimal-transport-for-offline-imitation#ran","syntology_url":"https://syntology.ai/paper/2303.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.13971"}},"official":{"repos":["ethanluoyc/optimal_transport_reward"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/how-to-guide-your-learner-imitation-learning","slug":"how-to-guide-your-learner-imitation-learning","title":"How To Guide Your Learner: Imitation Learning with Active Adaptive Expert Involvement","date":"2023-03-03","arxiv_id":"2303.02073","repositories_listed":1,"syntology":null},{"url":"/paper/teach-a-robot-to-fish-versatile-imitation","slug":"teach-a-robot-to-fish-versatile-imitation","title":"Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations","date":"2023-03-02","arxiv_id":"2303.01497","repositories_listed":1,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":1,"n_honours":2,"n_violates":1,"n_no_contract":8,"n_pointer_only":3,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 1 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/teach-a-robot-to-fish-versatile-imitation#ran","syntology_url":"https://syntology.ai/paper/2303.01497","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.01497"}},"official":{"repos":["siddhanthaldar/FISH"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/ls-iq-implicit-reward-regularization-for","slug":"ls-iq-implicit-reward-regularization-for","title":"LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning","date":"2023-03-01","arxiv_id":"2303.00599","repositories_listed":1,"syntology":null},{"url":"/paper/mega-dagger-imitation-learning-with-multiple","slug":"mega-dagger-imitation-learning-with-multiple","title":"MEGA-DAgger: Imitation Learning with Multiple Imperfect Experts","date":"2023-03-01","arxiv_id":"2303.00638","repositories_listed":1,"syntology":null},{"url":"/paper/learning-large-neighborhood-search-for","slug":"learning-large-neighborhood-search-for","title":"Learning Large Neighborhood Search for Vehicle Routing in Airport Ground Handling","date":"2023-02-27","arxiv_id":"2302.13797","repositories_listed":1,"syntology":null},{"url":"/paper/simulation-of-robot-swarms-for-learning","slug":"simulation-of-robot-swarms-for-learning","title":"Simulation of robot swarms for learning communication-aware coordination","date":"2023-02-25","arxiv_id":"2302.13124","repositories_listed":1,"syntology":null},{"url":"/paper/imitation-from-arbitrary-experience-a-dual","slug":"imitation-from-arbitrary-experience-a-dual","title":"Dual RL: Unification and New Methods for Reinforcement and Imitation Learning","date":"2023-02-16","arxiv_id":"2302.08560","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/imitation-from-arbitrary-experience-a-dual#ran","syntology_url":"https://syntology.ai/paper/2302.08560","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.08560"}},"official":{"repos":["hari-sikchi/DVL"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/pretraining-language-models-with-human","slug":"pretraining-language-models-with-human","title":"Pretraining Language Models with Human Preferences","date":"2023-02-16","arxiv_id":"2302.08582","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pretraining-language-models-with-human#ran","syntology_url":"https://syntology.ai/paper/2302.08582","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.08582"}},"official":{"repos":["tomekkorbak/pretraining-with-human-feedback"],"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":["found_in_text","official"]}}},{"url":"/paper/unlabeled-imperfect-demonstrations-in","slug":"unlabeled-imperfect-demonstrations-in","title":"Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning","date":"2023-02-13","arxiv_id":"2302.06271","repositories_listed":1,"syntology":null},{"url":"/paper/cilp-co-simulation-based-imitation-learner","slug":"cilp-co-simulation-based-imitation-learner","title":"CILP: Co-simulation based Imitation Learner for Dynamic Resource Provisioning in Cloud Computing Environments","date":"2023-02-11","arxiv_id":"2302.05630","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-generative-adversarial-imitation","slug":"hierarchical-generative-adversarial-imitation","title":"Hierarchical Generative Adversarial Imitation Learning with Mid-level Input Generation for Autonomous Driving on Urban Environments","date":"2023-02-09","arxiv_id":"2302.04823","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hierarchical-generative-adversarial-imitation#ran","syntology_url":"https://syntology.ai/paper/2302.04823","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.04823"}},"official":{"repos":["gustavokcouto/hgail"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-simulate-daily-activities-via","slug":"learning-to-simulate-daily-activities-via","title":"Learning to Simulate Daily Activities via Modeling Dynamic Human Needs","date":"2023-02-09","arxiv_id":"2302.10897","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/learning-to-simulate-daily-activities-via#ran","syntology_url":"https://syntology.ai/paper/2302.10897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.10897"}},"official":{"repos":["tsinghua-fib-lab/sand"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/maniskill2-a-unified-benchmark-for","slug":"maniskill2-a-unified-benchmark-for","title":"ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills","date":"2023-02-09","arxiv_id":"2302.04659","repositories_listed":1,"syntology":null},{"url":"/paper/robust-question-answering-against","slug":"robust-question-answering-against","title":"Robust Question Answering against Distribution Shifts with Test-Time Adaptation: An Empirical Study","date":"2023-02-09","arxiv_id":"2302.04618","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-affordance-annotation-for","slug":"fine-grained-affordance-annotation-for","title":"Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction Videos","date":"2023-02-07","arxiv_id":"2302.03292","repositories_listed":1,"syntology":null},{"url":"/paper/target-based-surrogates-for-stochastic","slug":"target-based-surrogates-for-stochastic","title":"Target-based Surrogates for Stochastic Optimization","date":"2023-02-06","arxiv_id":"2302.02607","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/target-based-surrogates-for-stochastic#ran","syntology_url":"https://syntology.ai/paper/2302.02607","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.02607"}},"official":{"repos":["wilderlavington/target-based-surrogates-for-stochastic-optimization"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-imitation-learning-with-patch-rewards","slug":"visual-imitation-learning-with-patch-rewards","title":"Visual Imitation Learning with Patch Rewards","date":"2023-02-02","arxiv_id":"2302.00965","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_honours":2,"n_violates":1,"n_no_contract":5,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/visual-imitation-learning-with-patch-rewards#ran","syntology_url":"https://syntology.ai/paper/2302.00965","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00965"}},"official":{"repos":["sail-sg/patchail"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/padl-language-directed-physics-based","slug":"padl-language-directed-physics-based","title":"PADL: Language-Directed Physics-Based Character Control","date":"2023-01-31","arxiv_id":"2301.13868","repositories_listed":1,"syntology":null},{"url":"/paper/superhuman-fairness","slug":"superhuman-fairness","title":"Superhuman Fairness","date":"2023-01-31","arxiv_id":"2301.13420","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-imitation-learning-with-vector","slug":"hierarchical-imitation-learning-with-vector","title":"Hierarchical Imitation Learning with Vector Quantized Models","date":"2023-01-30","arxiv_id":"2301.12962","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":8,"n_ran_checked":8,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"9 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hierarchical-imitation-learning-with-vector#ran","syntology_url":"https://syntology.ai/paper/2301.12962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12962"}},"official":null}},{"url":"/paper/optimal-decision-tree-policies-for-markov","slug":"optimal-decision-tree-policies-for-markov","title":"Optimal Decision Tree Policies for Markov Decision Processes","date":"2023-01-30","arxiv_id":"2301.13185","repositories_listed":1,"syntology":null},{"url":"/paper/winning-solution-of-real-robot-challenge-iii","slug":"winning-solution-of-real-robot-challenge-iii","title":"Identifying Expert Behavior in Offline Training Datasets Improves Behavioral Cloning of Robotic Manipulation Policies","date":"2023-01-30","arxiv_id":"2301.13019","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/winning-solution-of-real-robot-challenge-iii#ran","syntology_url":"https://syntology.ai/paper/2301.13019","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.13019"}},"official":{"repos":["wq13552463699/real-robot-challenge-2022"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/theoretical-analysis-of-offline-imitation","slug":"theoretical-analysis-of-offline-imitation","title":"Theoretical Analysis of Offline Imitation With Supplementary Dataset","date":"2023-01-27","arxiv_id":"2301.11687","repositories_listed":1,"syntology":null},{"url":"/paper/pirlnav-pretraining-with-imitation-and-rl","slug":"pirlnav-pretraining-with-imitation-and-rl","title":"PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav","date":"2023-01-18","arxiv_id":"2301.07302","repositories_listed":1,"syntology":null},{"url":"/paper/orbit-a-unified-simulation-framework-for","slug":"orbit-a-unified-simulation-framework-for","title":"Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments","date":"2023-01-10","arxiv_id":"2301.04195","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/orbit-a-unified-simulation-framework-for#ran","syntology_url":"https://syntology.ai/paper/2301.04195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.04195"}},"official":{"repos":["NVIDIA-Omniverse/Orbit"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-from-guided-play-improving","slug":"learning-from-guided-play-improving","title":"Learning from Guided Play: Improving Exploration for Adversarial Imitation Learning with Simple Auxiliary Tasks","date":"2022-12-30","arxiv_id":"2301.00051","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-imitation-learning-with-safety","slug":"end-to-end-imitation-learning-with-safety","title":"End-to-End Imitation Learning with Safety Guarantees using Control Barrier Functions","date":"2022-12-21","arxiv_id":"2212.11365","repositories_listed":1,"syntology":null},{"url":"/paper/cacti-a-framework-for-scalable-multi-task","slug":"cacti-a-framework-for-scalable-multi-task","title":"CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual Imitation Learning","date":"2022-12-12","arxiv_id":"2212.05711","repositories_listed":1,"syntology":null},{"url":"/paper/discovering-latent-knowledge-in-language","slug":"discovering-latent-knowledge-in-language","title":"Discovering Latent Knowledge in Language Models Without Supervision","date":"2022-12-07","arxiv_id":"2212.03827","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/discovering-latent-knowledge-in-language#ran","syntology_url":"https://syntology.ai/paper/2212.03827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03827"}},"official":{"repos":["collin-burns/discovering_latent_knowledge"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-imitation-learning-of-nonlinear-model","slug":"safe-imitation-learning-of-nonlinear-model","title":"Safe Imitation Learning of Nonlinear Model Predictive Control for Flexible Robots","date":"2022-12-06","arxiv_id":"2212.02941","repositories_listed":1,"syntology":null},{"url":"/paper/towards-improving-exploration-in-self","slug":"towards-improving-exploration-in-self","title":"Towards Improving Exploration in Self-Imitation Learning using Intrinsic Motivation","date":"2022-11-30","arxiv_id":"2211.16838","repositories_listed":1,"syntology":null},{"url":"/paper/a-system-for-morphology-task-generalization","slug":"a-system-for-morphology-task-generalization","title":"A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation","date":"2022-11-25","arxiv_id":"2211.14296","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-conditional-imitation-learning-for-1","slug":"dynamic-conditional-imitation-learning-for-1","title":"Dynamic Conditional Imitation Learning for Autonomous Driving","date":"2022-11-17","arxiv_id":"2211.11579","repositories_listed":1,"syntology":null},{"url":"/paper/follow-the-clairvoyant-an-imitation-learning","slug":"follow-the-clairvoyant-an-imitation-learning","title":"Follow the Clairvoyant: an Imitation Learning Approach to Optimal Control","date":"2022-11-14","arxiv_id":"2211.07389","repositories_listed":1,"syntology":null},{"url":"/paper/out-of-dynamics-imitation-learning-from","slug":"out-of-dynamics-imitation-learning-from","title":"Out-of-Dynamics Imitation Learning from Multimodal Demonstrations","date":"2022-11-13","arxiv_id":"2211.06839","repositories_listed":1,"syntology":null},{"url":"/paper/neuroceril-robotic-imitation-learning-via","slug":"neuroceril-robotic-imitation-learning-via","title":"NeuroCERIL: Robotic Imitation Learning via Hierarchical Cause-Effect Reasoning in Programmable Attractor Neural Networks","date":"2022-11-11","arxiv_id":"2211.06462","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-spiking-networks-the-computational","slug":"beyond-spiking-networks-the-computational","title":"Beyond spiking networks: the computational advantages of dendritic amplification and input segregation","date":"2022-11-04","arxiv_id":"2211.02553","repositories_listed":1,"syntology":null},{"url":"/paper/deconfounded-imitation-learning","slug":"deconfounded-imitation-learning","title":"Deconfounding Imitation Learning with Variational Inference","date":"2022-11-04","arxiv_id":"2211.02667","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-optimize-permutation-flow-shop","slug":"learning-to-optimize-permutation-flow-shop","title":"Learning to Optimize Permutation Flow Shop Scheduling via Graph-based Imitation Learning","date":"2022-10-31","arxiv_id":"2210.17178","repositories_listed":1,"syntology":null},{"url":"/paper/imitation-learning-based-implicit-semantic","slug":"imitation-learning-based-implicit-semantic","title":"Imitation Learning-based Implicit Semantic-aware Communication Networks: Multi-layer Representation and Collaborative Reasoning","date":"2022-10-28","arxiv_id":"2210.16118","repositories_listed":1,"syntology":null},{"url":"/paper/rate-splitting-for-intelligent-reflecting","slug":"rate-splitting-for-intelligent-reflecting","title":"Rate-Splitting for Intelligent Reflecting Surface-Aided Multiuser VR Streaming","date":"2022-10-21","arxiv_id":"2210.12191","repositories_listed":1,"syntology":null},{"url":"/paper/text-editing-as-imitation-game","slug":"text-editing-as-imitation-game","title":"Text Editing as Imitation Game","date":"2022-10-21","arxiv_id":"2210.12276","repositories_listed":1,"syntology":null},{"url":"/paper/diambra-arena-a-new-reinforcement-learning","slug":"diambra-arena-a-new-reinforcement-learning","title":"DIAMBRA Arena: a New Reinforcement Learning Platform for Research and Experimentation","date":"2022-10-19","arxiv_id":"2210.10595","repositories_listed":1,"syntology":null},{"url":"/paper/planning-for-sample-efficient-imitation","slug":"planning-for-sample-efficient-imitation","title":"Planning for Sample Efficient Imitation Learning","date":"2022-10-18","arxiv_id":"2210.09598","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":4,"n_ran_checked":5,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"8 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/planning-for-sample-efficient-imitation#ran","syntology_url":"https://syntology.ai/paper/2210.09598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.09598"}},"official":{"repos":["zhaohengyin/EfficientImitate"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}}],"record_sha256":"91dd337996bc61b7b14d428bd222d56126e066a45bdfd090cfdae0b907fd0450","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}