{"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/vintix-action-model-via-in-context","title":"Vintix: Action Model via In-Context Reinforcement Learning","arxiv_id":"2501.19400","date":"2025-01-31","proceeding":null,"authors":["Andrey Polubarov","Nikita Lyubaykin","Alexander Derevyagin","Ilya Zisman","Denis Tarasov","Alexander Nikulin","Vladislav Kurenkov"],"abstract":"In-Context Reinforcement Learning (ICRL) represents a promising paradigm for developing generalist agents that learn at inference time through trial-and-error interactions, analogous to how large language models adapt contextually, but with a focus on reward maximization. However, the scalability of ICRL beyond toy tasks and single-domain settings remains an open challenge. In this work, we present the first steps toward scaling ICRL by introducing a fixed, cross-domain model capable of learning behaviors through in-context reinforcement learning. Our results demonstrate that Algorithm Distillation, a framework designed to facilitate ICRL, offers a compelling and competitive alternative to expert distillation to construct versatile action models. These findings highlight the potential of ICRL as a scalable approach for generalist decision-making systems. Code to be released at https://github.com/dunnolab/vintix","url_abs":"https://arxiv.org/abs/2501.19400v1","url_pdf":"https://arxiv.org/pdf/2501.19400v1.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":"vintix-action-model-via-in-context","repo_url":"https://github.com/dunnolab/vintix","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":null,"task_name":"In-Context Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2501.19400","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.19400"}},"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/dunnolab/vintix","reach":null}],"summary":{"ran":4,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":7,"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":"81e363a4d42a6acf","entry":"ContinuousAcsEncoder","repo":"dunnolab/vintix","repo_kind":"official","path":"vintix/nn/individual_task_encoder.py","file_url":"https://github.com/dunnolab/vintix/blob/HEAD/vintix/nn/individual_task_encoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"81e363a4d42a6acf"}},{"code_sha256_prefix":"94fe9914b4618cec","entry":"LinearObsEncoder","repo":"dunnolab/vintix","repo_kind":"official","path":"vintix/nn/individual_task_encoder.py","file_url":"https://github.com/dunnolab/vintix/blob/HEAD/vintix/nn/individual_task_encoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"94fe9914b4618cec"}},{"code_sha256_prefix":"cd7f80d9a35a3e3a","entry":"RewardEncoder","repo":"dunnolab/vintix","repo_kind":"official","path":"vintix/nn/individual_task_encoder.py","file_url":"https://github.com/dunnolab/vintix/blob/HEAD/vintix/nn/individual_task_encoder.py","link_basis":"first_harvest_node","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":"cd7f80d9a35a3e3a"}},{"code_sha256_prefix":"21d4e50f8ea1c82c","entry":"get_acs_encoder","repo":"dunnolab/vintix","repo_kind":"official","path":"vintix/nn/individual_task_encoder.py","file_url":"https://github.com/dunnolab/vintix/blob/HEAD/vintix/nn/individual_task_encoder.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"21d4e50f8ea1c82c"}},{"code_sha256_prefix":"9e20e63115567301","entry":"get_obs_encoder","repo":"dunnolab/vintix","repo_kind":"official","path":"vintix/nn/individual_task_encoder.py","file_url":"https://github.com/dunnolab/vintix/blob/HEAD/vintix/nn/individual_task_encoder.py","link_basis":"first_harvest_node","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":"9e20e63115567301"}},{"code_sha256_prefix":"4d5af6687b20aa67","entry":"DiscreteAcsEncoder","repo":"dunnolab/vintix","repo_kind":"official","path":"vintix/nn/individual_task_encoder.py","file_url":"https://github.com/dunnolab/vintix/blob/HEAD/vintix/nn/individual_task_encoder.py","link_basis":"first_harvest_node","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":"4d5af6687b20aa67"}},{"code_sha256_prefix":"b8a3da843aa83b77","entry":"IndividualTaskEncoderNew","repo":"dunnolab/vintix","repo_kind":"official","path":"vintix/nn/individual_task_encoder.py","file_url":"https://github.com/dunnolab/vintix/blob/HEAD/vintix/nn/individual_task_encoder.py","link_basis":"first_harvest_node","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":"b8a3da843aa83b77"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}