{"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/meta-reinforcement-learning-with-autonomous-1","title":"Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies","arxiv_id":"2001.00248","date":"2020-01-01","proceeding":"ICLR 2020 1","authors":["Sungryull Sohn","Hyunjae Woo","Jongwook Choi","Honglak Lee"],"abstract":"We propose and address a novel few-shot RL problem, where a task is characterized by a subtask graph which describes a set of subtasks and their dependencies that are unknown to the agent. The agent needs to quickly adapt to the task over few episodes during adaptation phase to maximize the return in the test phase. Instead of directly learning a meta-policy, we develop a Meta-learner with Subtask Graph Inference(MSGI), which infers the latent parameter of the task by interacting with the environment and maximizes the return given the latent parameter. To facilitate learning, we adopt an intrinsic reward inspired by upper confidence bound (UCB) that encourages efficient exploration. Our experiment results on two grid-world domains and StarCraft II environments show that the proposed method is able to accurately infer the latent task parameter, and to adapt more efficiently than existing meta RL and hierarchical RL methods.","url_abs":"https://arxiv.org/abs/2001.00248v2","url_pdf":"https://arxiv.org/pdf/2001.00248v2.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":"meta-reinforcement-learning-with-autonomous-1","repo_url":"https://github.com/srsohn/msgi","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"efficient-exploration","task_name":"Efficient Exploration"},{"task_slug":"meta-reinforcement-learning","task_name":"Meta Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"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":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2001.00248","atlas_url":"https://app.syntology.ai/?focus=2001.00248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.00248"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/srsohn/msgi","reach":null}],"summary":{"ran":2,"ran_draft_wrong":2,"ran_honours":1},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":"e1cd54d98edcfe1f","entry":"ILP","repo":"srsohn/msgi","repo_kind":"official","path":"grid-world/graph/ILP.py","file_url":"https://github.com/srsohn/msgi/blob/HEAD/grid-world/graph/ILP.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":"e1cd54d98edcfe1f"}},{"code_sha256_prefix":"36db2ebee9fad758","entry":"_to_multi_hot","repo":"srsohn/msgi","repo_kind":"official","path":"grid-world/graph/ILP.py","file_url":"https://github.com/srsohn/msgi/blob/HEAD/grid-world/graph/ILP.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"36db2ebee9fad758"}},{"code_sha256_prefix":"81e43e94407ed380","entry":"_transform","repo":"srsohn/msgi","repo_kind":"official","path":"grid-world/graph/ILP.py","file_url":"https://github.com/srsohn/msgi/blob/HEAD/grid-world/graph/ILP.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"81e43e94407ed380"}},{"code_sha256_prefix":"9fd224ed549d872d","entry":"batch_bin_encode","repo":"srsohn/msgi","repo_kind":"official","path":"grid-world/graph/ILP.py","file_url":"https://github.com/srsohn/msgi/blob/HEAD/grid-world/graph/ILP.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9fd224ed549d872d"}},{"code_sha256_prefix":"11384de9305bcd32","entry":"dotdict","repo":"srsohn/msgi","repo_kind":"official","path":"grid-world/graph/ILP.py","file_url":"https://github.com/srsohn/msgi/blob/HEAD/grid-world/graph/ILP.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":"11384de9305bcd32"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}