{"id":"W3211776917","doi":"","title":"Learning Tree Interpretation from Object Representation for Deep Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; Simon Fraser University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Interpretation (philosophy); Representation (politics); Tree (set theory); Object (grammar); Machine learning; Programming language; 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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004221451,0.0002288821,0.0002775989,0.0002057532,0.0005597151,0.002059208,0.0004144181,0.0001199724,0.00001090143],"category_scores_gemma":[0.0008206819,0.0002360627,0.0001072625,0.00057236,0.00002454303,0.006271557,0.0001547688,0.0003532673,0.00007577864],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001724152,"about_ca_system_score_gemma":0.0001438727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005075337,"about_ca_topic_score_gemma":0.000003136137,"domain_scores_codex":[0.9975019,0.0001871035,0.0009978046,0.0003225041,0.0006337585,0.0003569815],"domain_scores_gemma":[0.9975975,0.0002629554,0.0009380265,0.0003202183,0.0007941189,0.0000872453],"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":[0.00001748815,0.000004292278,0.0004019147,0.0001654433,0.00002012419,0.000001455723,0.006884071,0.9243797,0.0004421686,0.0006171991,0.0001146863,0.06695144],"study_design_scores_gemma":[0.0006379387,0.0001477143,0.0002485222,0.0001776897,0.00001866052,0.00001812388,0.002458426,0.9895986,0.00194227,0.00004744602,0.004450831,0.0002537183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002678855,0.0001179146,0.9903236,0.000198287,0.0009509869,0.0004528187,5.00864e-7,0.0005036673,0.004773375],"genre_scores_gemma":[0.9891053,0.00001384428,0.008637907,0.0002271688,0.0001422342,0.0001315964,0.0004823991,0.00001711352,0.001242429],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9864265,"threshold_uncertainty_score":0.9989768,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02155870844513758,"score_gpt":0.2752711759624968,"score_spread":0.2537124675173592,"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."}}