{"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/a-composable-specification-language-for-1","title":"A Composable Specification Language for Reinforcement Learning Tasks","arxiv_id":"2008.09293","date":"2020-08-21","proceeding":"NeurIPS 2019 12","authors":["Kishor Jothimurugan","Rajeev Alur","Osbert Bastani"],"abstract":"Reinforcement learning is a promising approach for learning control policies for robot tasks. However, specifying complex tasks (e.g., with multiple objectives and safety constraints) can be challenging, since the user must design a reward function that encodes the entire task. Furthermore, the user often needs to manually shape the reward to ensure convergence of the learning algorithm. We propose a language for specifying complex control tasks, along with an algorithm that compiles specifications in our language into a reward function and automatically performs reward shaping. We implement our approach in a tool called SPECTRL, and show that it outperforms several state-of-the-art baselines.","url_abs":"https://arxiv.org/abs/2008.09293v2","url_pdf":"https://arxiv.org/pdf/2008.09293v2.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":"a-composable-specification-language-for-1","repo_url":"https://github.com/keyshor/spectrl_tool","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"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":{"atlas_url":"https://app.syntology.ai/?focus=2008.09293","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.09293"}},"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/keyshor/spectrl_tool","reach":null}],"summary":{"ran_draft_wrong":4,"unverified":2},"by_repo_kind":{"official":{"samples":6,"ran":4,"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":6,"samples":[{"code_sha256_prefix":"06d00e91fc2740f9","entry":"avoid","repo":"keyshor/spectrl_tool","repo_kind":"official","path":"spectrl/examples/car2d.py","file_url":"https://github.com/keyshor/spectrl_tool/blob/HEAD/spectrl/examples/car2d.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"06d00e91fc2740f9"}},{"code_sha256_prefix":"9c4c65ba5072ecc8","entry":"balance","repo":"keyshor/spectrl_tool","repo_kind":"official","path":"spectrl/examples/cartpole.py","file_url":"https://github.com/keyshor/spectrl_tool/blob/HEAD/spectrl/examples/cartpole.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9c4c65ba5072ecc8"}},{"code_sha256_prefix":"f17e2ee024593a43","entry":"reach","repo":"keyshor/spectrl_tool","repo_kind":"official","path":"spectrl/examples/car2d.py","file_url":"https://github.com/keyshor/spectrl_tool/blob/HEAD/spectrl/examples/car2d.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f17e2ee024593a43"}},{"code_sha256_prefix":"87dc028b039e3aaa","entry":"reach","repo":"keyshor/spectrl_tool","repo_kind":"official","path":"spectrl/examples/cartpole.py","file_url":"https://github.com/keyshor/spectrl_tool/blob/HEAD/spectrl/examples/cartpole.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"87dc028b039e3aaa"}},{"code_sha256_prefix":"35ccb4e3e91ec95a","entry":"resource_delta","repo":"keyshor/spectrl_tool","repo_kind":"official","path":"spectrl/examples/car2d.py","file_url":"https://github.com/keyshor/spectrl_tool/blob/HEAD/spectrl/examples/car2d.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"35ccb4e3e91ec95a"}},{"code_sha256_prefix":"0138ab067648cb60","entry":"resource_delta","repo":"keyshor/spectrl_tool","repo_kind":"official","path":"spectrl/examples/cartpole.py","file_url":"https://github.com/keyshor/spectrl_tool/blob/HEAD/spectrl/examples/cartpole.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0138ab067648cb60"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}