{"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/modular-lifelong-reinforcement-learning-via-1","title":"Modular Lifelong Reinforcement Learning via Neural Composition","arxiv_id":"2207.00429","date":"2022-07-01","proceeding":"ICLR 2022 4","authors":["Jorge A. Mendez","Harm van Seijen","Eric Eaton"],"abstract":"Humans commonly solve complex problems by decomposing them into easier subproblems and then combining the subproblem solutions. This type of compositional reasoning permits reuse of the subproblem solutions when tackling future tasks that share part of the underlying compositional structure. In a continual or lifelong reinforcement learning (RL) setting, this ability to decompose knowledge into reusable components would enable agents to quickly learn new RL tasks by leveraging accumulated compositional structures. We explore a particular form of composition based on neural modules and present a set of RL problems that intuitively admit compositional solutions. Empirically, we demonstrate that neural composition indeed captures the underlying structure of this space of problems. We further propose a compositional lifelong RL method that leverages accumulated neural components to accelerate the learning of future tasks while retaining performance on previous tasks via off-line RL over replayed experiences.","url_abs":"https://arxiv.org/abs/2207.00429v1","url_pdf":"https://arxiv.org/pdf/2207.00429v1.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":"modular-lifelong-reinforcement-learning-via-1","repo_url":"https://github.com/lifelong-ml/mendez2022modularlifelongrl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2207.00429","atlas_url":"https://app.syntology.ai/?focus=2207.00429","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.00429"}},"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/Lifelong-ML/Mendez2022ModularLifelongRL","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lifelong-ml/mendez2022modularlifelongrl","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"ran":1,"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":"beb7d468d5185af5","entry":"reject_next_to","repo":"Lifelong-ML/Mendez2022ModularLifelongRL","repo_kind":"official","path":"Discrete2D/gym-minigrid/gym_minigrid/roomgrid.py","file_url":"https://github.com/Lifelong-ML/Mendez2022ModularLifelongRL/blob/HEAD/Discrete2D/gym-minigrid/gym_minigrid/roomgrid.py","link_basis":"harvester_set","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":"beb7d468d5185af5"}},{"code_sha256_prefix":"59df34732c3e3418","entry":"downsample","repo":"Lifelong-ML/Mendez2022ModularLifelongRL","repo_kind":"official","path":"Discrete2D/gym-minigrid/gym_minigrid/rendering.py","file_url":"https://github.com/Lifelong-ML/Mendez2022ModularLifelongRL/blob/HEAD/Discrete2D/gym-minigrid/gym_minigrid/rendering.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":"59df34732c3e3418"}},{"code_sha256_prefix":"bd9c272b32f75522","entry":"fill_coords","repo":"Lifelong-ML/Mendez2022ModularLifelongRL","repo_kind":"official","path":"Discrete2D/gym-minigrid/gym_minigrid/rendering.py","file_url":"https://github.com/Lifelong-ML/Mendez2022ModularLifelongRL/blob/HEAD/Discrete2D/gym-minigrid/gym_minigrid/rendering.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":"bd9c272b32f75522"}},{"code_sha256_prefix":"8990d1cc61cec299","entry":"rotate_fn","repo":"Lifelong-ML/Mendez2022ModularLifelongRL","repo_kind":"official","path":"Discrete2D/gym-minigrid/gym_minigrid/rendering.py","file_url":"https://github.com/Lifelong-ML/Mendez2022ModularLifelongRL/blob/HEAD/Discrete2D/gym-minigrid/gym_minigrid/rendering.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":"8990d1cc61cec299"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}