{"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/flow-based-single-step-completion-for","title":"Flow-Based Single-Step Completion for Efficient and Expressive Policy Learning","arxiv_id":"2506.21427","date":"2025-06-26","proceeding":null,"authors":["Prajwal Koirala","Cody Fleming"],"abstract":"Generative models such as diffusion and flow-matching offer expressive policies for offline reinforcement learning (RL) by capturing rich, multimodal action distributions, but their iterative sampling introduces high inference costs and training instability due to gradient propagation across sampling steps. We propose the \\textit{Single-Step Completion Policy} (SSCP), a generative policy trained with an augmented flow-matching objective to predict direct completion vectors from intermediate flow samples, enabling accurate, one-shot action generation. In an off-policy actor-critic framework, SSCP combines the expressiveness of generative models with the training and inference efficiency of unimodal policies, without requiring long backpropagation chains. Our method scales effectively to offline, offline-to-online, and online RL settings, offering substantial gains in speed and adaptability over diffusion-based baselines. We further extend SSCP to goal-conditioned RL, enabling flat policies to exploit subgoal structures without explicit hierarchical inference. SSCP achieves strong results across standard offline RL and behavior cloning benchmarks, positioning it as a versatile, expressive, and efficient framework for deep RL and sequential decision-making.","url_abs":"https://arxiv.org/abs/2506.21427v1","url_pdf":"https://arxiv.org/pdf/2506.21427v1.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":[],"tasks":[{"task_slug":"action-generation","task_name":"Action Generation"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"offline-rl","task_name":"Offline RL"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"sequential-decision-making","task_name":"Sequential Decision Making"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2506.21427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.21427"}},"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/PrajwalKoirala/SSCP-Single-Step-Completion-Policy","reach":null}],"summary":{"ran":2,"ran_honours":1,"unverified":1},"by_repo_kind":{"found_in_text":{"samples":4,"ran":3,"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":4,"samples":[{"code_sha256_prefix":"933088029683db94","entry":"FourierFeatures","repo":"PrajwalKoirala/SSCP-Single-Step-Completion-Policy","repo_kind":"found_in_text","path":"SSCQL/agents/ssc_flow_policy.py","file_url":"https://github.com/PrajwalKoirala/SSCP-Single-Step-Completion-Policy/blob/HEAD/SSCQL/agents/ssc_flow_policy.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"933088029683db94"}},{"code_sha256_prefix":"945a9a1c3ed255be","entry":"ShortcutActorVectorField","repo":"PrajwalKoirala/SSCP-Single-Step-Completion-Policy","repo_kind":"found_in_text","path":"SSCQL/agents/ssc_flow_policy.py","file_url":"https://github.com/PrajwalKoirala/SSCP-Single-Step-Completion-Policy/blob/HEAD/SSCQL/agents/ssc_flow_policy.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"945a9a1c3ed255be"}},{"code_sha256_prefix":"7cfece344d630105","entry":"mish","repo":"PrajwalKoirala/SSCP-Single-Step-Completion-Policy","repo_kind":"found_in_text","path":"SSCQL/agents/ssc_flow_policy.py","file_url":"https://github.com/PrajwalKoirala/SSCP-Single-Step-Completion-Policy/blob/HEAD/SSCQL/agents/ssc_flow_policy.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7cfece344d630105"}},{"code_sha256_prefix":"0bf49a204582902d","entry":"SSC_Flow_Agent","repo":"PrajwalKoirala/SSCP-Single-Step-Completion-Policy","repo_kind":"found_in_text","path":"SSCQL/agents/ssc_flow_policy.py","file_url":"https://github.com/PrajwalKoirala/SSCP-Single-Step-Completion-Policy/blob/HEAD/SSCQL/agents/ssc_flow_policy.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":"0bf49a204582902d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}