{"id":"W2989640809","doi":"10.1609/aaai.v34i04.5857","title":"Algorithmic Improvements for Deep Reinforcement Learning Applied to Interactive Fiction","year":2020,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Compute Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Observability; Computer science; Artificial intelligence; Action (physics); Function (biology); Domain (mathematical analysis); Baseline (sea); Point (geometry); Machine learning; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007054564,0.0006790772,0.0007336997,0.0003337243,0.0003948246,0.0007753831,0.004670844,0.0003232534,0.00006249258],"category_scores_gemma":[0.001169633,0.0005967544,0.0003853615,0.0007258655,0.0002044039,0.0003851254,0.003566586,0.001342042,0.0001791733],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003446196,"about_ca_system_score_gemma":0.0002559127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008776887,"about_ca_topic_score_gemma":0.00001344408,"domain_scores_codex":[0.9952569,0.00002899711,0.001449597,0.001592796,0.0009583769,0.000713356],"domain_scores_gemma":[0.9959396,0.0002385497,0.00139706,0.0006348868,0.001531399,0.0002584734],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005093945,0.0002115961,0.00001828821,0.0003223693,0.000159123,6.366006e-7,0.01243653,0.05945044,0.07273891,0.5483825,0.000656368,0.3051139],"study_design_scores_gemma":[0.00001986805,0.0004047145,0.000007454544,0.0002994751,0.00002811158,5.954033e-7,0.001146816,0.4495961,0.4280668,0.1197968,0.0002530443,0.0003801598],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005622698,0.00001207392,0.9754496,0.004434192,0.002113433,0.003874668,0.000009597954,0.0002918209,0.008191884],"genre_scores_gemma":[0.9770008,0.00002778099,0.02072626,0.0006656739,0.0003371744,0.0009245969,0.000006825437,0.00005205327,0.0002588289],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9713781,"threshold_uncertainty_score":0.9996484,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0794015375588785,"score_gpt":0.3226425396400927,"score_spread":0.2432410020812142,"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."}}