{"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/xuance-a-comprehensive-and-unified-deep","title":"XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library","arxiv_id":"2312.16248","date":"2023-12-25","proceeding":null,"authors":["Wenzhang Liu","Wenzhe Cai","Kun Jiang","Guangran Cheng","Yuanda Wang","Jiawei Wang","Jingyu Cao","Lele Xu","Chaoxu Mu","Changyin Sun"],"abstract":"In this paper, we present XuanCe, a comprehensive and unified deep reinforcement learning (DRL) library designed to be compatible with PyTorch, TensorFlow, and MindSpore. XuanCe offers a wide range of functionalities, including over 40 classical DRL and multi-agent DRL algorithms, with the flexibility to easily incorporate new algorithms and environments. It is a versatile DRL library that supports CPU, GPU, and Ascend, and can be executed on various operating systems such as Ubuntu, Windows, MacOS, and EulerOS. Extensive benchmarks conducted on popular environments including MuJoCo, Atari, and StarCraftII multi-agent challenge demonstrate the library's impressive performance. XuanCe is open-source and can be accessed at https://github.com/agi-brain/xuance.git.","url_abs":"https://arxiv.org/abs/2312.16248v1","url_pdf":"https://arxiv.org/pdf/2312.16248v1.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":"xuance-a-comprehensive-and-unified-deep","repo_url":"https://github.com/agi-brain/xuance","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"mujoco","task_name":"MuJoCo"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":null,"method_name":"Library"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.16248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.16248"}},"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/agi-brain/xuance","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"ran_honours":1,"unverified":4},"by_repo_kind":{"official":{"samples":10,"ran":6,"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":"c306710732715c0c","entry":"compute_mean_std","repo":"agi-brain/xuance","repo_kind":"official","path":"xuance/common/offline_util.py","file_url":"https://github.com/agi-brain/xuance/blob/HEAD/xuance/common/offline_util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c306710732715c0c"}},{"code_sha256_prefix":"6bdf1d32a42dd9ed","entry":"create_memory","repo":"agi-brain/xuance","repo_kind":"official","path":"xuance/common/memory_tools.py","file_url":"https://github.com/agi-brain/xuance/blob/HEAD/xuance/common/memory_tools.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6bdf1d32a42dd9ed"}},{"code_sha256_prefix":"7e426e46e07822b2","entry":"load_yaml","repo":"agi-brain/xuance","repo_kind":"official","path":"xuance/common/common_tools.py","file_url":"https://github.com/agi-brain/xuance/blob/HEAD/xuance/common/common_tools.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7e426e46e07822b2"}},{"code_sha256_prefix":"ba80f9ff81b1de5f","entry":"normalize_states","repo":"agi-brain/xuance","repo_kind":"official","path":"xuance/common/offline_util.py","file_url":"https://github.com/agi-brain/xuance/blob/HEAD/xuance/common/offline_util.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ba80f9ff81b1de5f"}},{"code_sha256_prefix":"be548fd984bd5e7b","entry":"recursive_dict_update","repo":"agi-brain/xuance","repo_kind":"official","path":"xuance/common/common_tools.py","file_url":"https://github.com/agi-brain/xuance/blob/HEAD/xuance/common/common_tools.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"be548fd984bd5e7b"}},{"code_sha256_prefix":"921135160e526fe7","entry":"sample_batch","repo":"agi-brain/xuance","repo_kind":"official","path":"xuance/common/memory_tools.py","file_url":"https://github.com/agi-brain/xuance/blob/HEAD/xuance/common/memory_tools.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"921135160e526fe7"}},{"code_sha256_prefix":"5824a7722625e41d","entry":"get_arguments","repo":"agi-brain/xuance","repo_kind":"official","path":"xuance/common/common_tools.py","file_url":"https://github.com/agi-brain/xuance/blob/HEAD/xuance/common/common_tools.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5824a7722625e41d"}},{"code_sha256_prefix":"a4b161f2aea8c627","entry":"load_d4rl_dataset","repo":"agi-brain/xuance","repo_kind":"official","path":"xuance/common/offline_util.py","file_url":"https://github.com/agi-brain/xuance/blob/HEAD/xuance/common/offline_util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a4b161f2aea8c627"}},{"code_sha256_prefix":"5fd3703bcdef8cd3","entry":"mpi_mean","repo":"agi-brain/xuance","repo_kind":"official","path":"xuance/common/statistic_tools.py","file_url":"https://github.com/agi-brain/xuance/blob/HEAD/xuance/common/statistic_tools.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5fd3703bcdef8cd3"}},{"code_sha256_prefix":"2cf34e2bda814425","entry":"mpi_moments","repo":"agi-brain/xuance","repo_kind":"official","path":"xuance/common/statistic_tools.py","file_url":"https://github.com/agi-brain/xuance/blob/HEAD/xuance/common/statistic_tools.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2cf34e2bda814425"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}