{"id":"W1512866498","doi":"10.1609/aaai.v26i1.8321","title":"Investigating Contingency Awareness Using Atari 2600 Games","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"University of Alberta; Alberta Innovates; Western Canada Research Grid; Compute Canada","keywords":"Contingency; Reinforcement learning; Exploit; Computer science; Function (biology); Control (management); Value (mathematics); Reinforcement; Artificial intelligence; Contingency management; Bellman equation; Human–computer interaction; Machine learning; Psychology; Social psychology; Computer security","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000566803,0.0002732167,0.00033755,0.0001106747,0.0003872314,0.0005537325,0.002123381,0.000110995,0.00006721472],"category_scores_gemma":[0.001669783,0.0002312667,0.000141574,0.00107106,0.0003133959,0.0006359436,0.0009401903,0.0004276614,0.0000443355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007152263,"about_ca_system_score_gemma":0.0004359025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007468212,"about_ca_topic_score_gemma":0.000007666707,"domain_scores_codex":[0.9973864,0.0000376916,0.000762256,0.0006207523,0.0007198693,0.0004730254],"domain_scores_gemma":[0.9972873,0.0001459175,0.0006543864,0.0004873212,0.001306781,0.0001183018],"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":[0.000005902333,0.00006443905,0.00454756,0.00009498929,0.00002993782,0.000002039441,0.002074694,0.02340828,0.1324855,0.8216764,0.0000582216,0.01555209],"study_design_scores_gemma":[0.00002017332,0.00004760556,0.0002166911,0.0003652396,0.00001358381,0.000009669414,0.0005069002,0.4835393,0.483387,0.03159981,0.0000774367,0.0002166084],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3923892,0.00006939255,0.5905523,0.00259008,0.001215943,0.0003847014,0.000002659827,0.0002092542,0.01258648],"genre_scores_gemma":[0.9695887,0.00002295843,0.0296092,0.0002932278,0.00008402867,0.000008434507,7.464953e-7,0.00001757238,0.0003751554],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7900766,"threshold_uncertainty_score":0.9430783,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1387859785918386,"score_gpt":0.3272622020942906,"score_spread":0.188476223502452,"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."}}