{"id":"W4406121228","doi":"10.1007/s11633-023-1482-0","title":"Latent Landmark Graph for Efficient Exploration-exploitation Balance in Hierarchical Reinforcement Learning","year":2025,"lang":"en","type":"article","venue":"Machine Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Landmark; Reinforcement learning; Computer science; Reinforcement; Graph; Artificial intelligence; Balance (ability); Machine learning; Cognitive psychology; Psychology; Theoretical computer science; Social psychology; Neuroscience","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":[0.003680358,0.000189274,0.0002313981,0.00110383,0.0004046091,0.0003135171,0.001190339,0.00009577036,0.00002572372],"category_scores_gemma":[0.001488801,0.0001776398,0.00009071645,0.002144051,0.0001295675,0.000328968,0.0005013053,0.0009305504,0.0000662504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002825157,"about_ca_system_score_gemma":0.0002028616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001340365,"about_ca_topic_score_gemma":0.00002579552,"domain_scores_codex":[0.996673,0.0003843857,0.0006364285,0.0005956942,0.0009215277,0.0007889479],"domain_scores_gemma":[0.9974938,0.001341109,0.0000901149,0.0005466308,0.0004208642,0.0001075024],"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":[0.00005303531,0.00005287723,0.003030382,0.00007076732,0.00001300219,0.000004729477,0.001020528,0.8872873,0.0001490245,0.08907425,0.0001456115,0.01909846],"study_design_scores_gemma":[0.0002650169,0.0002791925,0.0005471583,0.0001533228,0.000002080536,8.885254e-7,0.0001733245,0.9839364,0.00242863,0.0100433,0.002010085,0.0001606124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002298519,0.0001593998,0.9903886,0.002864911,0.0002806332,0.0009823699,5.560393e-7,0.0001133204,0.002911665],"genre_scores_gemma":[0.9837756,0.0002296864,0.01262358,0.00009940509,0.00003703027,0.0003912197,0.00002767528,0.00001413934,0.002801687],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9814771,"threshold_uncertainty_score":0.7243941,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0638528454781579,"score_gpt":0.3792239764301926,"score_spread":0.3153711309520347,"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."}}