{"id":"W4414128997","doi":"10.1007/978-3-032-04558-4_8","title":"Learning to Optimize Entropy in the Soft Actor-Critic","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Reinforcement learning; Benchmarking; Regularization (linguistics); Entropy (arrow of time); Artificial neural network; Simulated annealing; Source code","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":[0.001873352,0.001241042,0.001621078,0.0005597576,0.0004230883,0.001324457,0.001437009,0.001582034,0.002654316],"category_scores_gemma":[0.005687859,0.0008120659,0.0004871612,0.0005292607,0.001844636,0.001605846,0.0021411,0.002314308,0.0005754026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001380659,"about_ca_system_score_gemma":0.00106153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002302196,"about_ca_topic_score_gemma":0.003468608,"domain_scores_codex":[0.9994757,0.0002214956,0.00002572369,0.00009586924,0.0001083858,0.00007283685],"domain_scores_gemma":[0.997627,0.00187486,0.0001198325,0.0001037134,0.0001802299,0.00009437678],"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":[0.0000659952,0.0000233518,0.0001928487,0.00006916469,0.00003930132,0.00002930151,0.00003122483,0.9488459,0.0008420983,0.03061875,0.0009394504,0.01830275],"study_design_scores_gemma":[0.000005538193,0.000008680281,0.00002147872,0.000005670144,0.000003348545,0.000004330675,0.000001466754,0.9904742,0.0001587713,0.009223349,0.00009053061,0.000002711302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01484714,0.0004415775,0.979403,0.0003365765,0.00008882636,0.00002644013,0.00003474548,0.0002599465,0.004561653],"genre_scores_gemma":[0.8441924,0.0004281674,0.1417047,0.0003053454,0.0002115201,0.0002006947,0.000111211,0.0003500522,0.01249593],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002654316,"threshold_uncertainty_score":0.0100174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01357638618321766,"score_gpt":0.2525143598403673,"score_spread":0.2389379736571496,"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."}}