{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000988232,0.0002345777,0.0002923037,0.0002618379,0.0002009952,0.0002259779,0.001847409,0.0001163277,0.00002925421],"category_scores_gemma":[0.0004834271,0.000192257,0.0001248316,0.001291844,0.0001395502,0.0003660372,0.0003022971,0.0004483723,0.00009933319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006735937,"about_ca_system_score_gemma":0.00008063376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001660364,"about_ca_topic_score_gemma":0.000004238305,"domain_scores_codex":[0.9976925,0.00001829651,0.0007004198,0.0004757336,0.0005396791,0.0005733526],"domain_scores_gemma":[0.9988997,0.0002173789,0.0001876043,0.0002608654,0.0003610982,0.00007337801],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004446092,0.00002177543,0.000302325,0.00004777159,0.00001004512,3.896717e-7,0.001401805,0.4316763,0.006701657,0.5496598,0.0001364651,0.009997107],"study_design_scores_gemma":[0.00006138445,0.0003342344,0.0001296653,0.0002325466,0.000007041366,0.000001035048,0.0003018947,0.895853,0.08019302,0.0222609,0.000404901,0.0002203232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04351798,0.000008755408,0.9415976,0.002451647,0.000602024,0.001009682,7.477175e-7,0.0002609395,0.01055066],"genre_scores_gemma":[0.9966988,0.00006158241,0.001290366,0.0001427663,0.0000485935,0.00009196417,0.00000177812,0.00001911365,0.001645059],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9531808,"threshold_uncertainty_score":0.7840015,"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."}}