{"id":"W4391021298","doi":"10.1109/cdc49753.2023.10383636","title":"Asymmetric Actor-Critic with Approximate Information State","year":2023,"lang":"en","type":"article","venue":"","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; Representation (politics); Markov decision process; Partially observable Markov decision process; State (computer science); Artificial intelligence; Observable; Complete information; Mathematical optimization; Markov chain; Theoretical computer science; Machine learning; Markov process; Algorithm; Mathematical economics; Markov model; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002451022,0.0000995306,0.00008847409,0.0004374763,0.00008871476,0.0003690896,0.000492638,0.00002383702,0.00001143757],"category_scores_gemma":[0.00006766589,0.00007541777,0.0000204174,0.002118905,0.00002130402,0.001964015,0.0001860261,0.0001007304,0.001328773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003443486,"about_ca_system_score_gemma":0.00004562846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001312102,"about_ca_topic_score_gemma":7.21118e-7,"domain_scores_codex":[0.9989359,0.00002001161,0.0001923028,0.0001274384,0.0004141057,0.000310221],"domain_scores_gemma":[0.9993137,0.00008377449,0.00006845812,0.0003714075,0.00009354133,0.00006911455],"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":[0.00000717828,0.00001139161,0.001769169,0.00009645347,0.00003306355,0.0000150335,0.001352754,0.876563,0.00002873067,0.05953629,0.006095842,0.05449108],"study_design_scores_gemma":[0.0002607164,0.000109572,0.004341302,0.00001066343,0.000002328868,0.000005709679,0.00004558187,0.9874638,0.0004099171,0.0003128552,0.006884916,0.0001526915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002074535,0.000002230332,0.9729562,0.0003217117,0.0001421373,0.0001419336,4.494466e-7,0.0009270727,0.02343377],"genre_scores_gemma":[0.9163602,0.00003145115,0.07760529,0.0007095516,0.00002110646,0.0000251767,0.00002755241,0.0000140755,0.005205617],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9142857,"threshold_uncertainty_score":0.9994488,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01139265128832747,"score_gpt":0.2245704851574752,"score_spread":0.2131778338691478,"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."}}