{"id":"W4382318178","doi":"10.1609/aaai.v37i8.26146","title":"Hypernetworks for Zero-Shot Transfer in Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Reinforcement learning; Computer science; Transfer of learning; Context (archaeology); Artificial intelligence; Task (project management); Set (abstract data type); Machine learning; Bellman equation; Mathematical optimization; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002038514,0.001090627,0.0009612848,0.000605786,0.000468758,0.0008578492,0.002093805,0.001633637,0.004278556],"category_scores_gemma":[0.00820599,0.0006409981,0.000575072,0.000415847,0.001576023,0.002186435,0.001918774,0.002833723,0.0006049636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001563889,"about_ca_system_score_gemma":0.0009000942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003029827,"about_ca_topic_score_gemma":0.003318734,"domain_scores_codex":[0.999393,0.0002520734,0.0000304908,0.0001562218,0.0001003161,0.00006789531],"domain_scores_gemma":[0.9973998,0.001837236,0.0001672893,0.0002544436,0.0002261884,0.0001151414],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007849577,0.00005240587,0.0003515521,0.00004811919,0.00002790287,0.0000566915,0.00006242241,0.942253,0.00104755,0.01740424,0.0009242505,0.03769342],"study_design_scores_gemma":[0.000005128734,0.00001608514,0.00002384254,0.000004485947,0.000002030574,0.000005096767,0.00000333525,0.9886183,0.0002496794,0.01089516,0.0001741303,0.000002835247],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01867681,0.0002566974,0.9774799,0.0002655532,0.00004794067,0.00006642163,0.00006974748,0.0007707645,0.002366131],"genre_scores_gemma":[0.8593943,0.0001950048,0.1339334,0.0003157037,0.00005250466,0.0004474616,0.0002476619,0.0002196563,0.005194176],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004278556,"threshold_uncertainty_score":0.01431322,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1140650363566056,"score_gpt":0.3095750642039231,"score_spread":0.1955100278473175,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}