{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/alphastar-unplugged-large-scale-offline","title":"AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning","arxiv_id":"2308.03526","date":"2023-08-07","proceeding":null,"authors":["Michaël Mathieu","Sherjil Ozair","Srivatsan Srinivasan","Caglar Gulcehre","Shangtong Zhang","Ray Jiang","Tom Le Paine","Richard Powell","Konrad Żołna","Julian Schrittwieser","David Choi","Petko Georgiev","Daniel Toyama","Aja Huang","Roman Ring","Igor Babuschkin","Timo Ewalds","Mahyar Bordbar","Sarah Henderson","Sergio Gómez Colmenarejo","Aäron van den Oord","Wojciech Marian Czarnecki","Nando de Freitas","Oriol Vinyals"],"abstract":"StarCraft II is one of the most challenging simulated reinforcement learning environments; it is partially observable, stochastic, multi-agent, and mastering StarCraft II requires strategic planning over long time horizons with real-time low-level execution. It also has an active professional competitive scene. StarCraft II is uniquely suited for advancing offline RL algorithms, both because of its challenging nature and because Blizzard has released a massive dataset of millions of StarCraft II games played by human players. This paper leverages that and establishes a benchmark, called AlphaStar Unplugged, introducing unprecedented challenges for offline reinforcement learning. We define a dataset (a subset of Blizzard's release), tools standardizing an API for machine learning methods, and an evaluation protocol. We also present baseline agents, including behavior cloning, offline variants of actor-critic and MuZero. We improve the state of the art of agents using only offline data, and we achieve 90% win rate against previously published AlphaStar behavior cloning agent.","url_abs":"https://arxiv.org/abs/2308.03526v1","url_pdf":"https://arxiv.org/pdf/2308.03526v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"alphastar-unplugged-large-scale-offline","repo_url":"https://github.com/deepmind/alphastar","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"offline-rl","task_name":"Offline RL"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"starcraft","task_name":"Starcraft"},{"task_slug":"starcraft-ii","task_name":"Starcraft II"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"accumulating-eligibility-trace","method_name":"Accumulating Eligibility Trace"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"alphastar","method_name":"AlphaStar"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"glu","method_name":"Gated Linear Unit"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"monte-carlo-tree-search","method_name":"Monte-Carlo Tree Search"},{"method_slug":"muzero","method_name":"MuZero"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"pointer-net","method_name":"Pointer Network"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"prioritized-experience-replay","method_name":"Prioritized Experience Replay"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"scatter-connection","method_name":"Scatter Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"td-lambda","method_name":"TD Lambda"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"v-trace","method_name":"V-trace"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2308.03526","atlas_url":"https://app.syntology.ai/?focus=2308.03526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.03526"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/deepmind/alphastar","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4},"by_repo_kind":{"named_in_paper":{"samples":4,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"fddd4de8642c0e47","entry":"add_warmup_to_schedule","repo":"deepmind/alphastar","repo_kind":"named_in_paper","path":"alphastar/modules/optimizers.py","file_url":"https://github.com/deepmind/alphastar/blob/HEAD/alphastar/modules/optimizers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fddd4de8642c0e47"}},{"code_sha256_prefix":"fd1fad33e04631e2","entry":"get_cosine_schedule","repo":"deepmind/alphastar","repo_kind":"named_in_paper","path":"alphastar/modules/optimizers.py","file_url":"https://github.com/deepmind/alphastar/blob/HEAD/alphastar/modules/optimizers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fd1fad33e04631e2"}},{"code_sha256_prefix":"9260cef62693f4b1","entry":"get_staircase_schedule","repo":"deepmind/alphastar","repo_kind":"named_in_paper","path":"alphastar/modules/optimizers.py","file_url":"https://github.com/deepmind/alphastar/blob/HEAD/alphastar/modules/optimizers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9260cef62693f4b1"}},{"code_sha256_prefix":"4dbef622383db864","entry":"is_transformer_arch","repo":"deepmind/alphastar","repo_kind":"named_in_paper","path":"alphastar/architectures/architectures.py","file_url":"https://github.com/deepmind/alphastar/blob/HEAD/alphastar/architectures/architectures.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4dbef622383db864"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}