{"id":"W4382239700","doi":"10.1609/aaai.v37i6.25825","title":"PiCor: Multi-Task Deep Reinforcement Learning with Policy Correction","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Task (project management); Computer science; Constraint (computer-aided design); Set (abstract data type); Artificial intelligence; Interference (communication); Machine learning; Channel (broadcasting); Mathematics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005351495,0.0002758915,0.0002541862,0.0003800448,0.0004148997,0.0003574103,0.001728827,0.0000934659,0.00002887965],"category_scores_gemma":[0.0007938605,0.0002029539,0.00009918239,0.002087838,0.0002273838,0.000511422,0.0005397301,0.0005300157,0.0003729894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001229593,"about_ca_system_score_gemma":0.0001633185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008954095,"about_ca_topic_score_gemma":0.000008455007,"domain_scores_codex":[0.9975906,0.00002457567,0.0005535978,0.0005091121,0.0007793089,0.0005427827],"domain_scores_gemma":[0.9982592,0.0001150111,0.0005440285,0.000348927,0.0006230652,0.0001097681],"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":[0.0000555641,0.00004277975,0.0008220025,0.00003776004,0.00002779413,0.000001078959,0.002780319,0.6785468,0.01101328,0.274564,0.0001377632,0.03197079],"study_design_scores_gemma":[0.00004972408,0.0004549513,0.0004169838,0.0001875002,0.000009677628,0.000005721463,0.0007641331,0.899115,0.09645052,0.002095362,0.0002178878,0.0002325844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0138855,0.000004568438,0.9710676,0.002180072,0.0007612227,0.000557791,2.533115e-7,0.0005298067,0.01101321],"genre_scores_gemma":[0.9934386,0.00005178451,0.002359709,0.000156595,0.00008464202,0.00003710558,0.000001447024,0.00002173315,0.003848389],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9795531,"threshold_uncertainty_score":0.8276221,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06260084640833517,"score_gpt":0.2989850664917558,"score_spread":0.2363842200834206,"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."}}