{"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/v-trace","slug":"v-trace","name":"V-trace","full_name":"V-trace","full_name_withheld":false,"description_markdown":"**V-trace** is an off-policy actor-critic reinforcement learning algorithm that helps tackle the lag between when actions are generated by the actors and when the learner estimates the gradient. Consider a trajectory $\\left(x\\_{t}, a\\_{t}, r\\_{t}\\right)^{t=s+n}\\_{t=s}$ generated by the actor following some policy $\\mu$. We can define the $n$-steps V-trace target for $V\\left(x\\_{s}\\right)$, our value approximation at state $x\\_{s}$ as:\r\n\r\n$$ v\\_{s} = V\\left(x\\_{s}\\right) + \\sum^{s+n-1}\\_{t=s}\\gamma^{t-s}\\left(\\prod^{t-1}\\_{i=s}c\\_{i}\\right)\\delta\\_{t}V $$\r\n\r\nWhere $\\delta\\_{t}V = \\rho\\_{t}\\left(r\\_{t} + \\gamma{V}\\left(x\\_{t+1}\\right) - V\\left(x\\_{t}\\right)\\right)$ is a temporal difference algorithm for $V$, and $\\rho\\_{t} = \\text{min}\\left(\\bar{\\rho}, \\frac{\\pi\\left(a\\_{t}\\mid{x\\_{t}}\\right)}{\\mu\\left(a\\_{t}\\mid{x\\_{t}}\\right)}\\right)$ and $c\\_{i} = \\text{min}\\left(\\bar{c}, \\frac{\\pi\\left(a\\_{t}\\mid{x\\_{t}}\\right)}{\\mu\\left(a\\_{t}\\mid{x\\_{t}}\\right)}\\right)$ are truncated importance sampling weights. We assume that the truncation levels are such that $\\bar{\\rho} \\geq \\bar{c}$.","description_state":"present","introduced_year":null,"introduced_by":{"title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","paper":"/paper/impala-scalable-distributed-deep-rl-with","first_author":"Lasse Espeholt","n_authors":12,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/impala-scalable-distributed-deep-rl-with"},"source":{"url":"http://arxiv.org/abs/1802.01561v3","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","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":34,"archive_num_papers":34,"papers_newest_first":[{"paper":"/paper/world-model-agents-with-change-based","slug":"world-model-agents-with-change-based","title":"World Model Agents with Change-Based Intrinsic Motivation","date":"2025-03-26","arxiv_id":"2503.21047","n_code_links":1,"syntology":null},{"paper":null,"slug":"vlearn-off-policy-learning-with-efficient","title":"Vlearn: Off-Policy Learning with Efficient State-Value Function Estimation","date":"2024-03-07","arxiv_id":"2403.04453","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-play-starcraft-ii","slug":"large-language-models-play-starcraft-ii","title":"Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach","date":"2023-12-19","arxiv_id":"2312.11865","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["histmeisah/large-language-models-play-starcraftii"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/cleanba-a-reproducible-and-efficient","slug":"cleanba-a-reproducible-and-efficient","title":"Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform","date":"2023-09-29","arxiv_id":"2310.00036","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":4,"n_instrument":0,"unverified":4,"pointer_only":8,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["vwxyzjn/cleanba"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-robust-and-opponent-aware-league-training","title":"A Robust and Opponent-Aware League Training Method for StarCraft II","date":"2023-09-21","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/alphastar-unplugged-large-scale-offline","slug":"alphastar-unplugged-large-scale-offline","title":"AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning","date":"2023-08-07","arxiv_id":"2308.03526","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/exploring-the-promise-and-limits-of-real-time","slug":"exploring-the-promise-and-limits-of-real-time","title":"Exploring the Promise and Limits of Real-Time Recurrent Learning","date":"2023-05-30","arxiv_id":"2305.19044","n_code_links":1,"syntology":null},{"paper":null,"slug":"domo-ac-doubly-multi-step-off-policy-actor","title":"DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm","date":"2023-05-29","arxiv_id":"2305.18501","n_code_links":0,"syntology":null},{"paper":"/paper/sharing-lifelong-reinforcement-learning","slug":"sharing-lifelong-reinforcement-learning","title":"Sharing Lifelong Reinforcement Learning Knowledge via Modulating Masks","date":"2023-05-18","arxiv_id":"2305.10997","n_code_links":2,"syntology":null},{"paper":"/paper/lifelong-reinforcement-learning-with","slug":"lifelong-reinforcement-learning-with","title":"Lifelong Reinforcement Learning with Modulating Masks","date":"2022-12-21","arxiv_id":"2212.11110","n_code_links":4,"syntology":null},{"paper":null,"slug":"accerl-policy-acceleration-framework-for-deep","title":"AcceRL: Policy Acceleration Framework for Deep Reinforcement Learning","date":"2022-11-28","arxiv_id":"2211.15023","n_code_links":0,"syntology":null},{"paper":"/paper/on-efficient-reinforcement-learning-for-full","slug":"on-efficient-reinforcement-learning-for-full","title":"On Efficient Reinforcement Learning for Full-length Game of StarCraft II","date":"2022-09-23","arxiv_id":"2209.11553","n_code_links":2,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["liuruoze/hiernet-sc2","liuruoze/mini-AlphaStar"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/envpool-a-highly-parallel-reinforcement","slug":"envpool-a-highly-parallel-reinforcement","title":"EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine","date":"2022-06-21","arxiv_id":"2206.10558","n_code_links":3,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sail-sg/envpool"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["named_in_paper","official"]}}},{"paper":null,"slug":"semantic-exploration-from-language","title":"Semantic Exploration from Language Abstractions and Pretrained Representations","date":"2022-04-08","arxiv_id":"2204.05080","n_code_links":0,"syntology":null},{"paper":"/paper/off-policy-correction-for-multi-agent","slug":"off-policy-correction-for-multi-agent","title":"Off-Policy Correction For Multi-Agent Reinforcement Learning","date":"2021-11-22","arxiv_id":"2111.11229","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["awarelab/seed_rl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"ai-in-games-techniques-challenges-and","title":"AI in Human-computer Gaming: Techniques, Challenges and Opportunities","date":"2021-11-15","arxiv_id":"2111.07631","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-distributed-deep-reinforcement-learning","title":"A Distributed Deep Reinforcement Learning Technique for Application Placement in Edge and Fog Computing Environments","date":"2021-10-24","arxiv_id":"2110.12415","n_code_links":0,"syntology":null},{"paper":"/paper/macrpo-multi-agent-cooperative-recurrent","slug":"macrpo-multi-agent-cooperative-recurrent","title":"MACRPO: Multi-Agent Cooperative Recurrent Policy Optimization","date":"2021-09-02","arxiv_id":"2109.00882","n_code_links":1,"syntology":null},{"paper":"/paper/rethinking-of-alphastar","slug":"rethinking-of-alphastar","title":"Rethinking of AlphaStar","date":"2021-08-07","arxiv_id":"2108.03452","n_code_links":2,"syntology":null},{"paper":"/paper/an-introduction-of-mini-alphastar","slug":"an-introduction-of-mini-alphastar","title":"An Introduction of mini-AlphaStar","date":"2021-04-14","arxiv_id":"2104.06890","n_code_links":1,"syntology":null},{"paper":null,"slug":"finite-sample-analysis-of-off-policy-natural","title":"Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm","date":"2021-02-18","arxiv_id":"2102.09318","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-lyapunov-theory-for-finite-sample","title":"A Lyapunov Theory for Finite-Sample Guarantees of Asynchronous Q-Learning and TD-Learning Variants","date":"2021-02-02","arxiv_id":"2102.01567","n_code_links":0,"syntology":null},{"paper":"/paper/deep-reinforcement-learning-with-function","slug":"deep-reinforcement-learning-with-function","title":"Deep Reinforcement Learning with Function Properties in Mean Reversion Strategies","date":"2021-01-09","arxiv_id":"2101.03418","n_code_links":1,"syntology":null},{"paper":"/paper/tstarbot-x-an-open-sourced-and-comprehensive","slug":"tstarbot-x-an-open-sourced-and-comprehensive","title":"TStarBot-X: An Open-Sourced and Comprehensive Study for Efficient League Training in StarCraft II Full Game","date":"2020-11-27","arxiv_id":"2011.13729","n_code_links":1,"syntology":null},{"paper":"/paper/particle-based-adaptive-discretization-for","slug":"particle-based-adaptive-discretization-for","title":"PFPN: Continuous Control of Physically Simulated Characters using Particle Filtering Policy Network","date":"2020-03-16","arxiv_id":"2003.06959","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-tuning-deep-reinforcement-learning","title":"A Self-Tuning Actor-Critic Algorithm","date":"2020-02-28","arxiv_id":"2002.12928","n_code_links":0,"syntology":null},{"paper":null,"slug":"finite-sample-analysis-of-stochastic","title":"Finite-Sample Analysis of Stochastic Approximation Using Smooth Convex Envelopes","date":"2020-02-03","arxiv_id":"2002.00874","n_code_links":0,"syntology":null},{"paper":null,"slug":"impact-importance-weighted-asynchronous-1","title":"IMPACT: Importance Weighted Asynchronous Architectures with Clipped Target Networks","date":"2019-11-30","arxiv_id":"1912.00167","n_code_links":0,"syntology":null},{"paper":"/paper/torchbeast-a-pytorch-platform-for-distributed","slug":"torchbeast-a-pytorch-platform-for-distributed","title":"TorchBeast: A PyTorch Platform for Distributed RL","date":"2019-10-08","arxiv_id":"1910.03552","n_code_links":3,"syntology":{"ran":6,"of":9,"n_ran_checked":2,"n_instrument":4,"unverified":3,"pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","official":{"repos":["heiner/scalable_agent"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/off-policy-actor-critic-with-shared-1","slug":"off-policy-actor-critic-with-shared-1","title":"Off-Policy Actor-Critic with Shared Experience Replay","date":"2019-09-25","arxiv_id":"1909.11583","n_code_links":0,"syntology":null},{"paper":"/paper/importance-resampling-for-off-policy","slug":"importance-resampling-for-off-policy","title":"Importance Resampling for Off-policy Prediction","date":"2019-06-11","arxiv_id":"1906.04328","n_code_links":2,"syntology":null},{"paper":null,"slug":"towards-combining-on-off-policy-methods-for","title":"Towards Combining On-Off-Policy Methods for Real-World Applications","date":"2019-04-24","arxiv_id":"1904.10642","n_code_links":0,"syntology":null},{"paper":null,"slug":"alphastar-an-evolutionary-computation","title":"AlphaStar: An Evolutionary Computation Perspective","date":"2019-02-05","arxiv_id":"1902.01724","n_code_links":0,"syntology":null},{"paper":"/paper/impala-scalable-distributed-deep-rl-with","slug":"impala-scalable-distributed-deep-rl-with","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","date":"2018-02-05","arxiv_id":"1802.01561","n_code_links":24,"syntology":{"ran":16,"of":34,"n_ran_checked":10,"n_instrument":6,"unverified":18,"pointer_only":3,"phrase":"16 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 18 unverified","official":{"repos":["deepmind/scalable_agent"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"papers_shown":34,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":34,"with_a_code_link":19,"where_syntology_ran_a_sample":8,"not_listed_spam_title":0,"listed":34,"listed_where_code_ran":8,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":7,"listed_every_run_a_failure_of_syntologys_instrument":1,"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":8,"papers_where_code_ran_first_page":"/method/v-trace/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/v-trace/papers/ran/1","json":"/method/v-trace/papers/ran/1.json","rows":8}],"tasks":[{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":18},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":15},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":14},{"task":"/task/starcraft","name":"Starcraft","papers":7},{"task":"/task/starcraft-ii","name":"Starcraft II","papers":7},{"task":"/task/deep-reinforcement-learning","name":"Deep Reinforcement Learning","papers":5},{"task":"/task/atari-games","name":"Atari Games","papers":3},{"task":"/task/decision-making","name":"Decision Making","papers":3},{"task":"/task/continuous-control","name":"Continuous Control","papers":2},{"task":"/task/lifelong-learning","name":"Lifelong learning","papers":2},{"task":"/task/openai-gym","name":"OpenAI Gym","papers":2},{"task":"/task/q-learning","name":"Q-Learning","papers":2},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":2},{"task":"/task/continuous-control","name":"continuous-control","papers":2},{"task":"/task/ai-agent","name":"AI Agent","papers":1},{"task":null,"name":"CPU","papers":1},{"task":"/task/diagnostic","name":"Diagnostic","papers":1},{"task":"/task/diversity","name":"Diversity","papers":1},{"task":"/task/edge-computing","name":"Edge-computing","papers":1},{"task":"/task/efficient-exploration","name":"Efficient Exploration","papers":1}],"tasks_shown":20,"n_tasks":31,"usage_by_year":[{"year":"2018","papers":1},{"year":"2019","papers":6},{"year":"2020","papers":4},{"year":"2021","papers":9},{"year":"2022","papers":5},{"year":"2023","papers":7},{"year":"2024","papers":1},{"year":"2025","papers":1}],"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/v-trace"},"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=V-trace","read_at":"2026-10-05T01:03:32+00:00","query":"V-trace","kind":"method","have":"no_code","tier":"paper_only","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"VTrace","origin_arxiv_id":"2609.37656"},"resolution":"token_match","resolved_name_differs":true,"absence_asserted":"for_this_exact_name_only","absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"different_paper","archive_paper_arxiv_id":"1802.01561","repositories":{"listed":null,"in_graph":0,"list_truncated":null,"strongest_link":null},"retrieve_with":null,"name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"2609.37656","citations":null},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'V-trace'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[{"name":"algorithm in the trace model setting","relation":"shares_name_tokens","relation_means":"shares name tokens with this name; a different method","level":3,"retrieve_with":"get_reference_implementation(name='algorithm in the trace model setting')","origin_arxiv_id":"2406.07253"}],"code_nearby_caption":"Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.","origin_paper":{"arxiv_id":"2609.37656","page":null,"syntology_url":null,"in_graph_layer":false,"samples":0},"line":"code not checked for this name. The lookup matched a different name in Syntology's graph, 'VTrace' (resolution: token_match), and its answer is about that name only, so it does not say whether this method has code. About another paper: this answer is about arXiv:2609.37656, while the archive credits arXiv:1802.01561.","level_legend":{"state":"quoted","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","card_sha256":"479785a84658dd682a11b10237b3620d651d7f87799f5dc7add970aaa83f6d39","note":"Syntology's served verification levels, quoted verbatim from its MCP server card; a row is split where the card separates clauses with a double hyphen, and the separator is not reproduced","levels":[{"level":"V0","quoted":["imports"]},{"level":"V1","quoted":["executes against a synthesized fixture and returns a value of the recorded type"]},{"level":"V2","quoted":["two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs","neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)"]},{"level":"V3","quoted":["paper-derived property tests pass on both of those same two generations."]}],"no_rung":"No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results."}},"syntology_have_state":"loaded","record_sha256":"758080c87196fd472b228c809c629f69861bbd2fce1cbe23fbc69bdf556b5e1f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}