{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002986863,0.002203124,0.001886727,0.0005275775,0.0005003473,0.001489552,0.001994871,0.001588998,0.002624417],"category_scores_gemma":[0.0119784,0.0006408711,0.0004730508,0.0004794899,0.001544947,0.002089861,0.002075026,0.003198908,0.0004687488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001818687,"about_ca_system_score_gemma":0.001777001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003638166,"about_ca_topic_score_gemma":0.00241743,"domain_scores_codex":[0.9983773,0.0005667973,0.00008937838,0.0003257639,0.0004465909,0.0001941546],"domain_scores_gemma":[0.9913034,0.006013717,0.0009586207,0.0007183765,0.0006651237,0.0003407623],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001152138,0.00003375108,0.0002858298,0.00004233483,0.00001725149,0.00004005067,0.00001869662,0.9822955,0.000421457,0.008408085,0.0003346862,0.007987075],"study_design_scores_gemma":[0.000006779555,0.00001372545,0.00001926505,0.000002736316,0.000002283382,0.000004002323,0.000001515801,0.9971849,0.0001607216,0.002543889,0.00005820472,0.000001934874],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0386112,0.000306867,0.9549397,0.0004633291,0.00005726707,0.00009506878,0.00008867413,0.0006660785,0.004771728],"genre_scores_gemma":[0.9458416,0.0001413114,0.05103174,0.0001426168,0.00003930007,0.0001535725,0.0001282318,0.00007273822,0.002448851],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003638166,"threshold_uncertainty_score":0.01579624,"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."}}