{"id":"W2198357760","doi":"10.1609/aaai.v29i1.9702","title":"Reward Shaping for Model-Based Bayesian Reinforcement Learning","year":2015,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Defense Acquisition Program Administration; Agency for Defense Development; National Research Foundation of Korea; Ministry of Science, ICT and Future Planning; National Research Foundation","keywords":"Reinforcement learning; Benchmark (surveying); Machine learning; Computer science; Artificial intelligence; Heuristic; Bayesian probability; Function (biology); Bayes' theorem; Domain (mathematical analysis); Bayesian inference; Mathematics","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":[0.001140777,0.0002775649,0.0003081477,0.000177235,0.0002809236,0.0003652497,0.002278399,0.0001109461,0.00001292398],"category_scores_gemma":[0.001330522,0.0002267418,0.0001665149,0.0005173348,0.0001813022,0.00048576,0.0003876268,0.0003803066,0.0000371666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001388898,"about_ca_system_score_gemma":0.0003417586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001287613,"about_ca_topic_score_gemma":0.000001328553,"domain_scores_codex":[0.9974481,0.00001891041,0.0007081486,0.0005191741,0.0007918,0.0005138134],"domain_scores_gemma":[0.9975086,0.0001196892,0.0005988046,0.000371339,0.001219575,0.0001819669],"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":[0.0000493977,0.00002073796,0.00005919392,0.00003630818,0.000008127585,1.014138e-7,0.0008066869,0.6225054,0.00167206,0.3696463,0.0001407265,0.005054983],"study_design_scores_gemma":[0.00006946929,0.0004113833,0.000002854199,0.0001938038,0.00001205,8.492195e-7,0.0002766949,0.8661893,0.09567428,0.03672359,0.0002148525,0.0002308703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001652961,0.000007817043,0.9836498,0.002458337,0.0003351276,0.000617107,5.580254e-7,0.0001618166,0.01111641],"genre_scores_gemma":[0.9567234,0.000004979996,0.04183935,0.0003723585,0.00006031104,0.00006340562,0.000001213728,0.00002164464,0.0009133192],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9550704,"threshold_uncertainty_score":0.9246262,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1686025736564232,"score_gpt":0.3233494496799389,"score_spread":0.1547468760235158,"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."}}