{"id":"W1904406446","doi":"","title":"Using predictive representations to improve generalization in reinforcement learning","year":2005,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Generalization; Reinforcement learning; Computer science; Representation (politics); Artificial intelligence; Task (project management); State (computer science); Machine learning; Grid; Reinforcement; Algorithm; Mathematics; Psychology; Social psychology; Engineering","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":[0.002006676,0.0007429364,0.0008366884,0.0004208118,0.0003070886,0.0008471475,0.001396029,0.001058007,0.002682223],"category_scores_gemma":[0.01356583,0.000397653,0.0004338291,0.0005516773,0.001186569,0.004002203,0.001765369,0.002088256,0.0004023072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007443744,"about_ca_system_score_gemma":0.0007303328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002330567,"about_ca_topic_score_gemma":0.001817291,"domain_scores_codex":[0.9993514,0.0002627637,0.00004375321,0.000141871,0.0001328205,0.00006735728],"domain_scores_gemma":[0.9944088,0.003787763,0.0003545029,0.0009051923,0.0004237799,0.0001198715],"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":[0.0002709912,0.0001788336,0.001239589,0.0001368982,0.00006549611,0.00008482992,0.0002127972,0.7449936,0.003694105,0.04053843,0.001858805,0.2067258],"study_design_scores_gemma":[0.00002794389,0.0001021297,0.0001735012,0.00001220581,0.00001189785,0.0000170255,0.00001164838,0.965212,0.001223294,0.03280805,0.0003897245,0.00001055044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08824538,0.00053411,0.9046426,0.0007173379,0.0000871283,0.00006676626,0.0001056886,0.001903695,0.003697289],"genre_scores_gemma":[0.9241363,0.0003044435,0.0735293,0.0002122391,0.00005621249,0.0001153841,0.0001370555,0.00008319116,0.001425826],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002682223,"threshold_uncertainty_score":0.01061249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02994124902249506,"score_gpt":0.3081307393099424,"score_spread":0.2781894902874474,"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."}}