{"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/merging-decision-transformers-weight","title":"Merging Decision Transformers: Weight Averaging for Forming Multi-Task Policies","arxiv_id":"2303.07551","date":"2023-03-14","proceeding":null,"authors":["Daniel Lawson","Ahmed H. Qureshi"],"abstract":"Recent work has shown the promise of creating generalist, transformer-based, models for language, vision, and sequential decision-making problems. To create such models, we generally require centralized training objectives, data, and compute. It is of interest if we can more flexibly create generalist policies by merging together multiple, task-specific, individually trained policies. In this work, we take a preliminary step in this direction through merging, or averaging, subsets of Decision Transformers in parameter space trained on different MuJoCo locomotion problems, forming multi-task models without centralized training. We also demonstrate the importance of various methodological choices when merging policies, such as utilizing common pre-trained initializations, increasing model capacity, and utilizing Fisher information for weighting parameter importance. In general, we believe research in this direction could help democratize and distribute the process that forms multi-task robotics policies. Our implementation is available at https://github.com/daniellawson9999/merging-decision-transformers.","url_abs":"https://arxiv.org/abs/2303.07551v3","url_pdf":"https://arxiv.org/pdf/2303.07551v3.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":"merging-decision-transformers-weight","repo_url":"https://github.com/daniellawson9999/merging-decision-transformers","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"mujoco","task_name":"MuJoCo"},{"task_slug":"sequential-decision-making","task_name":"Sequential Decision Making"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.07551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.07551"}},"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/daniellawson9999/merging-decision-transformers","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"unverified":7},"by_repo_kind":{"official":{"samples":8,"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":"0161b27cbe3cc58d","entry":"discount_cumsum","repo":"daniellawson9999/merging-decision-transformers","repo_kind":"official","path":"decision-transformer/experiment.py","file_url":"https://github.com/daniellawson9999/merging-decision-transformers/blob/HEAD/decision-transformer/experiment.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0161b27cbe3cc58d"}},{"code_sha256_prefix":"ce4536d70d1e91b4","entry":"get_action","repo":"daniellawson9999/merging-decision-transformers","repo_kind":"official","path":"decision-transformer/dt_utils.py","file_url":"https://github.com/daniellawson9999/merging-decision-transformers/blob/HEAD/decision-transformer/dt_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ce4536d70d1e91b4"}},{"code_sha256_prefix":"e0ebd221e411b411","entry":"get_dataset","repo":"daniellawson9999/merging-decision-transformers","repo_kind":"official","path":"decision-transformer/experiment_multi.py","file_url":"https://github.com/daniellawson9999/merging-decision-transformers/blob/HEAD/decision-transformer/experiment_multi.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e0ebd221e411b411"}},{"code_sha256_prefix":"731fbc6e43e42ea6","entry":"get_name_dataset","repo":"daniellawson9999/merging-decision-transformers","repo_kind":"official","path":"decision-transformer/mergeff_tripple.py","file_url":"https://github.com/daniellawson9999/merging-decision-transformers/blob/HEAD/decision-transformer/mergeff_tripple.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"731fbc6e43e42ea6"}},{"code_sha256_prefix":"aea7fd58cf32ead3","entry":"get_name_dataset","repo":"daniellawson9999/merging-decision-transformers","repo_kind":"official","path":"decision-transformer/mergeff_tripple_fish.py","file_url":"https://github.com/daniellawson9999/merging-decision-transformers/blob/HEAD/decision-transformer/mergeff_tripple_fish.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aea7fd58cf32ead3"}},{"code_sha256_prefix":"cb4e99dd4b50f69d","entry":"load_tf_weights_in_gpt2","repo":"daniellawson9999/merging-decision-transformers","repo_kind":"official","path":"decision-transformer/decision_transformer/models/trajectory_gpt2.py","file_url":"https://github.com/daniellawson9999/merging-decision-transformers/blob/HEAD/decision-transformer/decision_transformer/models/trajectory_gpt2.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cb4e99dd4b50f69d"}},{"code_sha256_prefix":"287524513504e252","entry":"weight_average","repo":"daniellawson9999/merging-decision-transformers","repo_kind":"official","path":"decision-transformer/dt_utils.py","file_url":"https://github.com/daniellawson9999/merging-decision-transformers/blob/HEAD/decision-transformer/dt_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"287524513504e252"}},{"code_sha256_prefix":"7e06a1bac726af66","entry":"weight_average_multi","repo":"daniellawson9999/merging-decision-transformers","repo_kind":"official","path":"decision-transformer/dt_utils.py","file_url":"https://github.com/daniellawson9999/merging-decision-transformers/blob/HEAD/decision-transformer/dt_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7e06a1bac726af66"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}