{"id":"W4417538955","doi":"10.48550/arxiv.2506.16608","title":"Distributions as Actions: A Unified Framework for Diverse Action Spaces","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Action (physics); Parameterized complexity; Simple (philosophy); Boundary (topology); Space (punctuation); Distribution (mathematics); Variance (accounting)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002366068,0.0003122979,0.0003006808,0.0002048132,0.0004320691,0.0003718886,0.001308231,0.0004845196,0.0000335371],"category_scores_gemma":[0.0009838697,0.0003351814,0.0002533597,0.0004481345,0.00007558565,0.0003489606,0.001588138,0.001028543,0.00018653],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003091065,"about_ca_system_score_gemma":0.0003970901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001223681,"about_ca_topic_score_gemma":0.00001068986,"domain_scores_codex":[0.9981575,0.00008279797,0.0003508732,0.0007169602,0.0002939797,0.0003979121],"domain_scores_gemma":[0.9973892,0.0005322296,0.0003772671,0.001329461,0.0002636978,0.0001081377],"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":[0.00004689511,0.0001519251,0.02849998,0.0004663507,0.0004695202,0.00001019184,0.0009481903,0.4665247,0.0001030559,0.4892309,0.009328101,0.004220123],"study_design_scores_gemma":[0.001729985,0.0006090534,0.06102813,0.002789577,0.0008052226,0.00001762284,0.001531311,0.40568,0.004919242,0.1268441,0.3909664,0.003079376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01682474,0.00004917646,0.9730045,0.002815196,0.004099702,0.0007399998,0.00004730792,0.0005132295,0.001906149],"genre_scores_gemma":[0.8049205,0.0004330534,0.1727677,0.0005951984,0.0006532207,0.0005455685,0.0004064733,0.00003241758,0.01964591],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8002368,"threshold_uncertainty_score":0.99991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1296206952545041,"score_gpt":0.3684946699910031,"score_spread":0.2388739747364989,"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."}}