{"id":"W3037991458","doi":"","title":"What can I do here? A Theory of Affordances in Reinforcement Learning","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Affordance; Reinforcement learning; Computer science; Markov decision process; Embodied cognition; Context (archaeology); Dual (grammatical number); Function (biology); Artificial intelligence; Human–computer interaction; Cognitive science; Markov process; Mathematics; Psychology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009293382,0.0003717078,0.0005893979,0.0002680226,0.00005676098,0.0005854834,0.002212768,0.0002141147,0.0001037028],"category_scores_gemma":[0.0002073882,0.0003477199,0.0001445853,0.0004049869,0.00009147065,0.0005212282,0.003687158,0.001196147,0.00002805442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001542994,"about_ca_system_score_gemma":0.0003329745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000789523,"about_ca_topic_score_gemma":0.00001763796,"domain_scores_codex":[0.9970017,0.0002639111,0.0008462834,0.0007382817,0.0007166125,0.0004332051],"domain_scores_gemma":[0.9979261,0.0002436853,0.0006441229,0.0009649104,0.00010318,0.0001180062],"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":[0.00001101348,0.000009263737,0.0006608165,0.0002185873,0.00004361856,0.00001361945,0.005261922,0.8757232,0.00003929733,0.1131054,0.00004526855,0.004867892],"study_design_scores_gemma":[0.0004957881,0.0003372681,0.0003555872,0.001369138,0.00001890036,0.000003286834,0.003494735,0.9718924,0.001311442,0.01890113,0.001141097,0.0006792304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002000702,0.0004304921,0.9787099,0.0008860592,0.001185132,0.0004843009,2.604052e-7,0.0002077736,0.01609532],"genre_scores_gemma":[0.9663422,0.000955757,0.02837955,0.0003466166,0.00006566236,0.00004360117,0.00001524318,0.00002626684,0.003825068],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9643415,"threshold_uncertainty_score":0.9998975,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03236714438760317,"score_gpt":0.2685764085169631,"score_spread":0.2362092641293599,"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."}}