{"id":"W4393159809","doi":"10.1609/aaai.v38i10.28970","title":"Contextual Pre-planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Transfer of learning; Cognitive psychology; Machine learning; Psychology; Social 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001045606,0.0007436522,0.0007448792,0.0002718035,0.0003071199,0.0006107449,0.001128566,0.0007602126,0.002534057],"category_scores_gemma":[0.004879512,0.0004206197,0.0003756271,0.000272241,0.001125838,0.001488523,0.001602562,0.002009892,0.0003398452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009782019,"about_ca_system_score_gemma":0.0012166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00306074,"about_ca_topic_score_gemma":0.003689719,"domain_scores_codex":[0.9996177,0.0001454069,0.00001939944,0.00008865491,0.00006989411,0.0000588063],"domain_scores_gemma":[0.9983728,0.001032492,0.0001502719,0.0002309935,0.0001078525,0.0001054954],"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":[0.0001162962,0.0001032275,0.0006356619,0.00005352708,0.0000211599,0.00006029937,0.0001034039,0.928771,0.002459962,0.01236099,0.0008023371,0.05451202],"study_design_scores_gemma":[0.000007910686,0.00002972944,0.0000491446,0.000003916089,0.000002541629,0.000004424575,0.000004601676,0.9910693,0.0005283452,0.008136575,0.0001605772,0.000002822407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07160936,0.0002484555,0.9246992,0.0002912731,0.00004019336,0.00005930452,0.00007039437,0.001311337,0.001670457],"genre_scores_gemma":[0.924444,0.0001029149,0.07359917,0.000103551,0.00001882928,0.0001165168,0.00009991446,0.00007900817,0.001436079],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00306074,"threshold_uncertainty_score":0.008477271,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06539929613530107,"score_gpt":0.3236612521517399,"score_spread":0.2582619560164389,"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."}}