{"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/not-all-tasks-are-equally-difficult-multi","title":"Not All Tasks Are Equally Difficult: Multi-Task Deep Reinforcement Learning with Dynamic Depth Routing","arxiv_id":"2312.14472","date":"2023-12-22","proceeding":null,"authors":["Jinmin He","Kai Li","Yifan Zang","Haobo Fu","Qiang Fu","Junliang Xing","Jian Cheng"],"abstract":"Multi-task reinforcement learning endeavors to accomplish a set of different tasks with a single policy. To enhance data efficiency by sharing parameters across multiple tasks, a common practice segments the network into distinct modules and trains a routing network to recombine these modules into task-specific policies. However, existing routing approaches employ a fixed number of modules for all tasks, neglecting that tasks with varying difficulties commonly require varying amounts of knowledge. This work presents a Dynamic Depth Routing (D2R) framework, which learns strategic skipping of certain intermediate modules, thereby flexibly choosing different numbers of modules for each task. Under this framework, we further introduce a ResRouting method to address the issue of disparate routing paths between behavior and target policies during off-policy training. In addition, we design an automatic route-balancing mechanism to encourage continued routing exploration for unmastered tasks without disturbing the routing of mastered ones. We conduct extensive experiments on various robotics manipulation tasks in the Meta-World benchmark, where D2R achieves state-of-the-art performance with significantly improved learning efficiency.","url_abs":"https://arxiv.org/abs/2312.14472v2","url_pdf":"https://arxiv.org/pdf/2312.14472v2.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":"not-all-tasks-are-equally-difficult-multi","repo_url":"https://github.com/DarkDawn233/D2R_MTRL","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2312.14472","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14472"}},"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/DarkDawn233/D2R_MTRL","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"official":{"samples":8,"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":0,"samples":[{"code_sha256_prefix":"2810eeadc3f8ff21","entry":"calc_next_shape","repo":"DarkDawn233/D2R_MTRL","repo_kind":"official","path":"torchrl/networks/utils/base.py","file_url":"https://github.com/DarkDawn233/D2R_MTRL/blob/HEAD/torchrl/networks/utils/base.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":"2810eeadc3f8ff21"}},{"code_sha256_prefix":"c31cb0cb3f1f949f","entry":"huber","repo":"DarkDawn233/D2R_MTRL","repo_kind":"official","path":"torchrl/algo/utils.py","file_url":"https://github.com/DarkDawn233/D2R_MTRL/blob/HEAD/torchrl/algo/utils.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c31cb0cb3f1f949f"}},{"code_sha256_prefix":"cf204748769747b0","entry":"null_activation","repo":"DarkDawn233/D2R_MTRL","repo_kind":"official","path":"torchrl/networks/depth_route_net.py","file_url":"https://github.com/DarkDawn233/D2R_MTRL/blob/HEAD/torchrl/networks/depth_route_net.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cf204748769747b0"}},{"code_sha256_prefix":"f25a7e88ddd2a04b","entry":"sample_gumbel","repo":"DarkDawn233/D2R_MTRL","repo_kind":"official","path":"torchrl/networks/depth_route_net.py","file_url":"https://github.com/DarkDawn233/D2R_MTRL/blob/HEAD/torchrl/networks/depth_route_net.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f25a7e88ddd2a04b"}},{"code_sha256_prefix":"b54e9f49009c2aaa","entry":"get_env","repo":"DarkDawn233/D2R_MTRL","repo_kind":"official","path":"torchrl/env/get_env.py","file_url":"https://github.com/DarkDawn233/D2R_MTRL/blob/HEAD/torchrl/env/get_env.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":"b54e9f49009c2aaa"}},{"code_sha256_prefix":"60be26f7786be240","entry":"get_task_info","repo":"DarkDawn233/D2R_MTRL","repo_kind":"official","path":"torchrl/env/get_env.py","file_url":"https://github.com/DarkDawn233/D2R_MTRL/blob/HEAD/torchrl/env/get_env.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":"60be26f7786be240"}},{"code_sha256_prefix":"adc57a9c56af85dc","entry":"quantile_regression_loss","repo":"DarkDawn233/D2R_MTRL","repo_kind":"official","path":"torchrl/algo/utils.py","file_url":"https://github.com/DarkDawn233/D2R_MTRL/blob/HEAD/torchrl/algo/utils.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":"adc57a9c56af85dc"}},{"code_sha256_prefix":"04e45d83caac37a8","entry":"unsqe_cat_gather","repo":"DarkDawn233/D2R_MTRL","repo_kind":"official","path":"torchrl/algo/utils.py","file_url":"https://github.com/DarkDawn233/D2R_MTRL/blob/HEAD/torchrl/algo/utils.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":"04e45d83caac37a8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}