{"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/mask-based-latent-reconstruction-for","title":"Mask-based Latent Reconstruction for Reinforcement Learning","arxiv_id":"2201.12096","date":"2022-01-28","proceeding":null,"authors":["Tao Yu","Zhizheng Zhang","Cuiling Lan","Yan Lu","Zhibo Chen"],"abstract":"For deep reinforcement learning (RL) from pixels, learning effective state representations is crucial for achieving high performance. However, in practice, limited experience and high-dimensional inputs prevent effective representation learning. To address this, motivated by the success of mask-based modeling in other research fields, we introduce mask-based reconstruction to promote state representation learning in RL. Specifically, we propose a simple yet effective self-supervised method, Mask-based Latent Reconstruction (MLR), to predict complete state representations in the latent space from the observations with spatially and temporally masked pixels. MLR enables better use of context information when learning state representations to make them more informative, which facilitates the training of RL agents. Extensive experiments show that our MLR significantly improves the sample efficiency in RL and outperforms the state-of-the-art sample-efficient RL methods on multiple continuous and discrete control benchmarks. Our code is available at https://github.com/microsoft/Mask-based-Latent-Reconstruction.","url_abs":"https://arxiv.org/abs/2201.12096v3","url_pdf":"https://arxiv.org/pdf/2201.12096v3.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":"mask-based-latent-reconstruction-for","repo_url":"https://github.com/microsoft/Mask-based-Latent-Reconstruction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2201.12096","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.12096"}},"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":"deterministic:regex_extraction","url":"https://github.com/microsoft/Mask-based-Latent-Reconstruction","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/microsoft/Playvirtual","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/google-research/rliable","reach":null}],"summary":{"ran":6,"ran_draft_wrong":1,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1},"found_in_text":{"samples":6,"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":"f7a03dfc44c34334","entry":"Conv2dSame","repo":"microsoft/Playvirtual","repo_kind":"found_in_text","path":"Atari/src/models.py","file_url":"https://github.com/microsoft/Playvirtual/blob/HEAD/Atari/src/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f7a03dfc44c34334"}},{"code_sha256_prefix":"1ef174de7e17cfd1","entry":"CubeMaskGenerator","repo":"microsoft/Mask-based-Latent-Reconstruction","repo_kind":"official","path":"DMControl/src/mtm_sac.py","file_url":"https://github.com/microsoft/Mask-based-Latent-Reconstruction/blob/HEAD/DMControl/src/mtm_sac.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":"1ef174de7e17cfd1"}},{"code_sha256_prefix":"0b8b5b709ce22b1e","entry":"PositionalEmbedding","repo":"microsoft/Mask-based-Latent-Reconstruction","repo_kind":"official","path":"DMControl/src/mtm_sac.py","file_url":"https://github.com/microsoft/Mask-based-Latent-Reconstruction/blob/HEAD/DMControl/src/mtm_sac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0b8b5b709ce22b1e"}},{"code_sha256_prefix":"bcd2e1b0c4219ca6","entry":"ResidualBlock","repo":"microsoft/Playvirtual","repo_kind":"found_in_text","path":"Atari/src/models.py","file_url":"https://github.com/microsoft/Playvirtual/blob/HEAD/Atari/src/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bcd2e1b0c4219ca6"}},{"code_sha256_prefix":"54f31a99fd9cb94b","entry":"RewardPredictor","repo":"microsoft/Playvirtual","repo_kind":"found_in_text","path":"Atari/src/models.py","file_url":"https://github.com/microsoft/Playvirtual/blob/HEAD/Atari/src/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"54f31a99fd9cb94b"}},{"code_sha256_prefix":"f9e622f31f261cbe","entry":"TransitionModel","repo":"microsoft/Playvirtual","repo_kind":"found_in_text","path":"Atari/src/models.py","file_url":"https://github.com/microsoft/Playvirtual/blob/HEAD/Atari/src/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f9e622f31f261cbe"}},{"code_sha256_prefix":"5298669e4fe00d40","entry":"init_normalization","repo":"microsoft/Playvirtual","repo_kind":"found_in_text","path":"Atari/src/models.py","file_url":"https://github.com/microsoft/Playvirtual/blob/HEAD/Atari/src/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5298669e4fe00d40"}},{"code_sha256_prefix":"fa63400bb2942968","entry":"renormalize","repo":"microsoft/Playvirtual","repo_kind":"found_in_text","path":"Atari/src/models.py","file_url":"https://github.com/microsoft/Playvirtual/blob/HEAD/Atari/src/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fa63400bb2942968"}},{"code_sha256_prefix":"7a1c73da025130f7","entry":"MTM","repo":"microsoft/Mask-based-Latent-Reconstruction","repo_kind":"official","path":"DMControl/src/mtm_sac.py","file_url":"https://github.com/microsoft/Mask-based-Latent-Reconstruction/blob/HEAD/DMControl/src/mtm_sac.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":"7a1c73da025130f7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}