{"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/drs-learning-reusable-dense-rewards-for-multi","title":"DrS: Learning Reusable Dense Rewards for Multi-Stage Tasks","arxiv_id":"2404.16779","date":"2024-04-25","proceeding":null,"authors":["Tongzhou Mu","Minghua Liu","Hao Su"],"abstract":"The success of many RL techniques heavily relies on human-engineered dense rewards, which typically demand substantial domain expertise and extensive trial and error. In our work, we propose DrS (Dense reward learning from Stages), a novel approach for learning reusable dense rewards for multi-stage tasks in a data-driven manner. By leveraging the stage structures of the task, DrS learns a high-quality dense reward from sparse rewards and demonstrations if given. The learned rewards can be \\textit{reused} in unseen tasks, thus reducing the human effort for reward engineering. Extensive experiments on three physical robot manipulation task families with 1000+ task variants demonstrate that our learned rewards can be reused in unseen tasks, resulting in improved performance and sample efficiency of RL algorithms. The learned rewards even achieve comparable performance to human-engineered rewards on some tasks. See our project page (https://sites.google.com/view/iclr24drs) for more details.","url_abs":"https://arxiv.org/abs/2404.16779v1","url_pdf":"https://arxiv.org/pdf/2404.16779v1.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":"drs-learning-reusable-dense-rewards-for-multi","repo_url":"https://github.com/tongzhoumu/DrS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"robot-manipulation","task_name":"Robot Manipulation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.16779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.16779"}},"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/tongzhoumu/DrS","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"listed":{"samples":5,"ran":0,"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":"524fb5bacf0cfab4","entry":"collect_episode_info","repo":"tongzhoumu/DrS","repo_kind":"listed","path":"drs/drs_learn_reward_maniskill2.py","file_url":"https://github.com/tongzhoumu/DrS/blob/HEAD/drs/drs_learn_reward_maniskill2.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":"524fb5bacf0cfab4"}},{"code_sha256_prefix":"322670cb8fb632dd","entry":"evaluate","repo":"tongzhoumu/DrS","repo_kind":"listed","path":"drs/drs_reuse_reward_maniskill2.py","file_url":"https://github.com/tongzhoumu/DrS/blob/HEAD/drs/drs_reuse_reward_maniskill2.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":"322670cb8fb632dd"}},{"code_sha256_prefix":"d1e665d55d4cc1c9","entry":"load_demo_dataset","repo":"tongzhoumu/DrS","repo_kind":"listed","path":"drs/data_utils.py","file_url":"https://github.com/tongzhoumu/DrS/blob/HEAD/drs/data_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":"d1e665d55d4cc1c9"}},{"code_sha256_prefix":"a8e6fb9649b99318","entry":"load_raw_trajectories","repo":"tongzhoumu/DrS","repo_kind":"listed","path":"drs/data_utils.py","file_url":"https://github.com/tongzhoumu/DrS/blob/HEAD/drs/data_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":"a8e6fb9649b99318"}},{"code_sha256_prefix":"f2ef64ecb943576d","entry":"sample_from_multi_buffers","repo":"tongzhoumu/DrS","repo_kind":"listed","path":"drs/drs_learn_reward_maniskill2.py","file_url":"https://github.com/tongzhoumu/DrS/blob/HEAD/drs/drs_learn_reward_maniskill2.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":"f2ef64ecb943576d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}