{"id":"W3136492000","doi":"10.1177/1059712321999421","title":"Affordance as general value function: a computational model","year":2021,"lang":"en","type":"article","venue":"Adaptive Behavior","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; Huawei Technologies (Canada)","funders":"","keywords":"Affordance; Computer science; Perception; Reinforcement learning; Artificial intelligence; Action (physics); Function (biology); Cognitive science; Perspective (graphical); Explication; Value (mathematics); Scalability; Human–computer interaction; Machine learning; Psychology; Epistemology","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":[0.0005690302,0.0006265444,0.0007798225,0.0006319053,0.0004326164,0.001820635,0.001682535,0.001769329,0.00513769],"category_scores_gemma":[0.002537148,0.0004763967,0.001213337,0.0007300507,0.002438933,0.004250416,0.001419204,0.002370953,0.0006703595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001074997,"about_ca_system_score_gemma":0.0008252139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004329198,"about_ca_topic_score_gemma":0.002995213,"domain_scores_codex":[0.9997349,0.00008669947,0.00001178577,0.00007773915,0.00005416307,0.00003469661],"domain_scores_gemma":[0.9994647,0.0003133194,0.00006041017,0.00006251107,0.00004667317,0.00005235898],"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":[0.00001706924,0.00001864976,0.0003509505,0.00005505103,0.00002261566,0.0000726747,0.0001038929,0.2581765,0.000608452,0.7303839,0.001205551,0.008984589],"study_design_scores_gemma":[0.000007043022,0.0000161904,0.0001316269,0.00001737664,0.000007821309,0.00004167553,0.000014789,0.5596939,0.00009375458,0.4377488,0.002216755,0.00001031526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02418678,0.001330969,0.9487096,0.002708036,0.00008721212,0.00003804866,0.0003791184,0.000297735,0.02226256],"genre_scores_gemma":[0.8253174,0.002539676,0.1540893,0.0004802608,0.0001712419,0.0003173947,0.0003320563,0.0001825862,0.01656999],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00513769,"threshold_uncertainty_score":0.01718724,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03032992744357185,"score_gpt":0.2752280964595858,"score_spread":0.2448981690160139,"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."}}