{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/stochastic-dueling-network","slug":"stochastic-dueling-network","name":"Stochastic Dueling Network","full_name":"Stochastic Dueling Network","full_name_withheld":false,"description_markdown":"A **Stochastic Dueling Network**, or **SDN**, is an architecture for learning a value function $V$. The SDN learns both $V$ and $Q$ off-policy while maintaining consistency between the two estimates. At each time step it outputs a stochastic estimate of $Q$ and a deterministic estimate of $V$.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Sample Efficient Actor-Critic with Experience Replay","paper":"/paper/sample-efficient-actor-critic-with-experience","first_author":"Ziyu Wang","n_authors":7,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/sample-efficient-actor-critic-with-experience"},"source":{"url":"http://arxiv.org/abs/1611.01224v2","title":"Sample Efficient Actor-Critic with Experience Replay","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Reinforcement Learning","area_id":"reinforcement-learning","collection":"Value Function Estimation","url":"/methods/category/value-function-estimation","pwc_aliases":[]}],"n_papers_tagged":12,"archive_num_papers":12,"papers_newest_first":[{"paper":null,"slug":"dynamics-of-resource-allocation-in-o-rans-an","title":"Dynamics of Resource Allocation in O-RANs: An In-depth Exploration of On-Policy and Off-Policy Deep Reinforcement Learning for Real-Time Applications","date":"2024-11-17","arxiv_id":"2412.01839","n_code_links":0,"syntology":null},{"paper":"/paper/joint-physical-digital-facial-attack","slug":"joint-physical-digital-facial-attack","title":"Joint Physical-Digital Facial Attack Detection Via Simulating Spoofing Clues","date":"2024-04-12","arxiv_id":"2404.08450","n_code_links":3,"syntology":null},{"paper":null,"slug":"distributional-estimation-of-data-uncertainty","title":"Distributional Estimation of Data Uncertainty for Surveillance Face Anti-spoofing","date":"2023-09-18","arxiv_id":"2309.09485","n_code_links":0,"syntology":null},{"paper":null,"slug":"pdvn-a-patch-based-dual-view-network-for-face","title":"PDVN: A Patch-based Dual-view Network for Face Liveness Detection using Light Field Focal Stack","date":"2023-01-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"asynchronous-curriculum-experience-replay-a","title":"Asynchronous Curriculum Experience Replay: A Deep Reinforcement Learning Approach for UAV Autonomous Motion Control in Unknown Dynamic Environments","date":"2022-07-04","arxiv_id":"2207.01251","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-word-error-rate-a-good-evaluation-metric","title":"Is Word Error Rate a good evaluation metric for Speech Recognition in Indic Languages?","date":"2022-03-30","arxiv_id":"2203.16601","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-reward-machines-a-study-in-partially","title":"Learning Reward Machines: A Study in Partially Observable Reinforcement Learning","date":"2021-12-17","arxiv_id":"2112.09477","n_code_links":0,"syntology":null},{"paper":"/paper/a-deeppixbis-attentional-angular-margin-for","slug":"a-deeppixbis-attentional-angular-margin-for","title":"A-DeepPixBis: Attentional Angular Margin for Face Anti-Spoofing","date":"2021-03-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/learning-reward-machines-for-partially","slug":"learning-reward-machines-for-partially","title":"Learning Reward Machines for Partially Observable Reinforcement Learning","date":"2019-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"sample-efficient-deep-reinforcement-learning","title":"Sample Efficient Deep Reinforcement Learning for Dialogue Systems with Large Action Spaces","date":"2018-02-11","arxiv_id":"1802.03753","n_code_links":0,"syntology":null},{"paper":null,"slug":"pretraining-deep-actor-critic-reinforcement","title":"Pretraining Deep Actor-Critic Reinforcement Learning Algorithms With Expert Demonstrations","date":"2018-01-31","arxiv_id":"1801.10459","n_code_links":0,"syntology":null},{"paper":"/paper/sample-efficient-actor-critic-with-experience","slug":"sample-efficient-actor-critic-with-experience","title":"Sample Efficient Actor-Critic with Experience Replay","date":"2016-11-03","arxiv_id":"1611.01224","n_code_links":7,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":null}}],"papers_shown":12,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":12,"with_a_code_link":3,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":12,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[],"tasks":[{"task":"/task/deep-reinforcement-learning","name":"Deep Reinforcement Learning","papers":5},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":5},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":5},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":5},{"task":"/task/face-anti-spoofing","name":"Face Anti-Spoofing","papers":3},{"task":"/task/face-recognition","name":"Face Recognition","papers":3},{"task":"/task/partially-observable-reinforcement-learning","name":"Partially Observable Reinforcement Learning","papers":2},{"task":"/task/problem-decomposition","name":"Problem Decomposition","papers":2},{"task":"/task/automatic-speech-recognition-2","name":"Automatic Speech Recognition","papers":1},{"task":"/task/automatic-speech-recognition","name":"Automatic Speech Recognition (ASR)","papers":1},{"task":"/task/benchmarking","name":"Benchmarking","papers":1},{"task":"/task/binary-classification","name":"Binary Classification","papers":1},{"task":"/task/continuous-control","name":"Continuous Control","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/face-presentation-attack-detection","name":"Face Presentation Attack Detection","papers":1},{"task":"/task/architecture-search","name":"Neural Architecture Search","papers":1},{"task":"/task/speech-recognition","name":"Speech Recognition","papers":1},{"task":"/task/spoken-dialogue-systems","name":"Spoken Dialogue Systems","papers":1},{"task":"/task/continuous-control","name":"continuous-control","papers":1},{"task":"/task/speech-recognition-1","name":"speech-recognition","papers":1}],"tasks_shown":20,"n_tasks":20,"usage_by_year":[{"year":"2016","papers":1},{"year":"2018","papers":2},{"year":"2019","papers":1},{"year":"2021","papers":2},{"year":"2022","papers":2},{"year":"2023","papers":2},{"year":"2024","papers":2}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/stochastic-dueling-network"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Stochastic%20Dueling%20Network","read_at":"2026-10-05T01:02:39+00:00","query":"Stochastic Dueling Network","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"1611.01224","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'Stochastic Dueling Network' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["stochastic RMD","Stochastic-YOLO","stochastic depth","Stochastic Hi-Fi","stochastic AC-FGM","Stochastic Lifting","Row-Stochastic SVRG","Stochastic Attention"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"da979c8a4e230bda30de48d0791f2821d5c5a04336bf1c60ec4f347182f96d4b","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}