{"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/on-efficient-reinforcement-learning-for-full","title":"On Efficient Reinforcement Learning for Full-length Game of StarCraft II","arxiv_id":"2209.11553","date":"2022-09-23","proceeding":null,"authors":["Ruo-Ze Liu","Zhen-Jia Pang","Zhou-Yu Meng","Wenhai Wang","Yang Yu","Tong Lu"],"abstract":"StarCraft II (SC2) poses a grand challenge for reinforcement learning (RL), of which the main difficulties include huge state space, varying action space, and a long time horizon. In this work, we investigate a set of RL techniques for the full-length game of StarCraft II. We investigate a hierarchical RL approach involving extracted macro-actions and a hierarchical architecture of neural networks. We investigate a curriculum transfer training procedure and train the agent on a single machine with 4 GPUs and 48 CPU threads. On a 64x64 map and using restrictive units, we achieve a win rate of 99% against the level-1 built-in AI. Through the curriculum transfer learning algorithm and a mixture of combat models, we achieve a 93% win rate against the most difficult non-cheating level built-in AI (level-7). In this extended version of the paper, we improve our architecture to train the agent against the cheating level AIs and achieve the win rate against the level-8, level-9, and level-10 AIs as 96%, 97%, and 94%, respectively. Our codes are at https://github.com/liuruoze/HierNet-SC2. To provide a baseline referring the AlphaStar for our work as well as the research and open-source community, we reproduce a scaled-down version of it, mini-AlphaStar (mAS). The latest version of mAS is 1.07, which can be trained on the raw action space which has 564 actions. It is designed to run training on a single common machine, by making the hyper-parameters adjustable. We then compare our work with mAS using the same resources and show that our method is more effective. The codes of mini-AlphaStar are at https://github.com/liuruoze/mini-AlphaStar. We hope our study could shed some light on the future research of efficient reinforcement learning on SC2 and other large-scale games.","url_abs":"https://arxiv.org/abs/2209.11553v1","url_pdf":"https://arxiv.org/pdf/2209.11553v1.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":"on-efficient-reinforcement-learning-for-full","repo_url":"https://github.com/liuruoze/hiernet-sc2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"on-efficient-reinforcement-learning-for-full","repo_url":"https://github.com/liuruoze/mini-AlphaStar","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"starcraft","task_name":"Starcraft"},{"task_slug":"starcraft-ii","task_name":"Starcraft II"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"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":"mas","method_name":"MAS"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"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":"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":{"atlas_url":"https://app.syntology.ai/?focus=2209.11553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.11553"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/liuruoze/mini-AlphaStar","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/liuruoze/hiernet-sc2","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":10},"by_repo_kind":{"official":{"samples":10,"ran":0,"repositories":2}},"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":"5fb7f59bf558201f","entry":"check_info","repo":"liuruoze/mini-AlphaStar","repo_kind":"official","path":"alphastarmini/core/sl/analyze_alphastar_replay.py","file_url":"https://github.com/liuruoze/mini-AlphaStar/blob/HEAD/alphastarmini/core/sl/analyze_alphastar_replay.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5fb7f59bf558201f"}},{"code_sha256_prefix":"25312448061ef152","entry":"conv2d_layer","repo":"liuruoze/hiernet-sc2","repo_kind":"official","path":"lib/layer.py","file_url":"https://github.com/liuruoze/hiernet-sc2/blob/HEAD/lib/layer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"25312448061ef152"}},{"code_sha256_prefix":"f39f7f97825609d2","entry":"dense_layer","repo":"liuruoze/hiernet-sc2","repo_kind":"official","path":"lib/layer.py","file_url":"https://github.com/liuruoze/hiernet-sc2/blob/HEAD/lib/layer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f39f7f97825609d2"}},{"code_sha256_prefix":"273b3f4951d282a9","entry":"hammingDist","repo":"liuruoze/mini-AlphaStar","repo_kind":"official","path":"alphastarmini/lib/edit_distance.py","file_url":"https://github.com/liuruoze/mini-AlphaStar/blob/HEAD/alphastarmini/lib/edit_distance.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"273b3f4951d282a9"}},{"code_sha256_prefix":"fe097265b3baf872","entry":"intprod","repo":"liuruoze/hiernet-sc2","repo_kind":"official","path":"lib/adversary.py","file_url":"https://github.com/liuruoze/hiernet-sc2/blob/HEAD/lib/adversary.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fe097265b3baf872"}},{"code_sha256_prefix":"b47feca24bd7a593","entry":"levenshtein_recur","repo":"liuruoze/mini-AlphaStar","repo_kind":"official","path":"alphastarmini/lib/edit_distance.py","file_url":"https://github.com/liuruoze/mini-AlphaStar/blob/HEAD/alphastarmini/lib/edit_distance.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b47feca24bd7a593"}},{"code_sha256_prefix":"b670203d64a57c2a","entry":"max_pool","repo":"liuruoze/hiernet-sc2","repo_kind":"official","path":"lib/layer.py","file_url":"https://github.com/liuruoze/hiernet-sc2/blob/HEAD/lib/layer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b670203d64a57c2a"}},{"code_sha256_prefix":"f77b8cc87eb232fd","entry":"numel","repo":"liuruoze/hiernet-sc2","repo_kind":"official","path":"lib/adversary.py","file_url":"https://github.com/liuruoze/hiernet-sc2/blob/HEAD/lib/adversary.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f77b8cc87eb232fd"}},{"code_sha256_prefix":"4be1fe2ffcfbdb85","entry":"time_wait","repo":"liuruoze/hiernet-sc2","repo_kind":"official","path":"lib/config.py","file_url":"https://github.com/liuruoze/hiernet-sc2/blob/HEAD/lib/config.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4be1fe2ffcfbdb85"}},{"code_sha256_prefix":"ba0d14a7eba757e3","entry":"var_shape","repo":"liuruoze/hiernet-sc2","repo_kind":"official","path":"lib/adversary.py","file_url":"https://github.com/liuruoze/hiernet-sc2/blob/HEAD/lib/adversary.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ba0d14a7eba757e3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}