{"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/boosting-long-delayed-reinforcement-learning","title":"Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays","arxiv_id":"2402.03141","date":"2024-02-05","proceeding":null,"authors":["Qingyuan Wu","Simon Sinong Zhan","YiXuan Wang","Yuhui Wang","Chung-Wei Lin","Chen Lv","Qi Zhu","Jürgen Schmidhuber","Chao Huang"],"abstract":"Reinforcement learning (RL) is challenging in the common case of delays between events and their sensory perceptions. State-of-the-art (SOTA) state augmentation techniques either suffer from state space explosion or performance degeneration in stochastic environments. To address these challenges, we present a novel Auxiliary-Delayed Reinforcement Learning (AD-RL) method that leverages auxiliary tasks involving short delays to accelerate RL with long delays, without compromising performance in stochastic environments. Specifically, AD-RL learns a value function for short delays and uses bootstrapping and policy improvement techniques to adjust it for long delays. We theoretically show that this can greatly reduce the sample complexity. On deterministic and stochastic benchmarks, our method significantly outperforms the SOTAs in both sample efficiency and policy performance. Code is available at https://github.com/QingyuanWuNothing/AD-RL.","url_abs":"https://arxiv.org/abs/2402.03141v2","url_pdf":"https://arxiv.org/pdf/2402.03141v2.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":"boosting-long-delayed-reinforcement-learning","repo_url":"https://github.com/qingyuanwunothing/ad-rl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.03141","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03141"}},"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/QingyuanWuNothing/AD-RL","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/qingyuanwunothing/ad-rl","reach":{"status":"ok"}}],"summary":{"ran":9,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":11,"ran":10,"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":11,"samples":[{"code_sha256_prefix":"d27cd46bef9cd5a7","entry":"action_value","repo":"QingyuanWuNothing/AD-RL","repo_kind":"official","path":"DETERMINISTIC-MDP.py","file_url":"https://github.com/QingyuanWuNothing/AD-RL/blob/HEAD/DETERMINISTIC-MDP.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":"d27cd46bef9cd5a7"}},{"code_sha256_prefix":"8d481d190b83d758","entry":"find_specific_exp_tag","repo":"QingyuanWuNothing/AD-RL","repo_kind":"official","path":"utils.py","file_url":"https://github.com/QingyuanWuNothing/AD-RL/blob/HEAD/utils.py","link_basis":"harvester_set","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":"8d481d190b83d758"}},{"code_sha256_prefix":"4562c1fef99e80f7","entry":"greedy_action","repo":"QingyuanWuNothing/AD-RL","repo_kind":"official","path":"DETERMINISTIC-MDP.py","file_url":"https://github.com/QingyuanWuNothing/AD-RL/blob/HEAD/DETERMINISTIC-MDP.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":"4562c1fef99e80f7"}},{"code_sha256_prefix":"beb42d440ccf2925","entry":"layer_init","repo":"QingyuanWuNothing/AD-RL","repo_kind":"official","path":"nn.py","file_url":"https://github.com/QingyuanWuNothing/AD-RL/blob/HEAD/nn.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"beb42d440ccf2925"}},{"code_sha256_prefix":"c21517332c327b92","entry":"make_anneal_lr","repo":"QingyuanWuNothing/AD-RL","repo_kind":"official","path":"utils.py","file_url":"https://github.com/QingyuanWuNothing/AD-RL/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c21517332c327b92"}},{"code_sha256_prefix":"7c5acb79755772b3","entry":"make_classical_env","repo":"QingyuanWuNothing/AD-RL","repo_kind":"official","path":"make_env.py","file_url":"https://github.com/QingyuanWuNothing/AD-RL/blob/HEAD/make_env.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":"7c5acb79755772b3"}},{"code_sha256_prefix":"954a62d688488366","entry":"make_classical_obs_delay_env","repo":"QingyuanWuNothing/AD-RL","repo_kind":"official","path":"make_env.py","file_url":"https://github.com/QingyuanWuNothing/AD-RL/blob/HEAD/make_env.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":"954a62d688488366"}},{"code_sha256_prefix":"bdf1781d7265fc58","entry":"make_linear_schedule","repo":"QingyuanWuNothing/AD-RL","repo_kind":"official","path":"utils.py","file_url":"https://github.com/QingyuanWuNothing/AD-RL/blob/HEAD/utils.py","link_basis":"harvester_set","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":"bdf1781d7265fc58"}},{"code_sha256_prefix":"af3f16c8beef0513","entry":"make_vector_classical_envs","repo":"QingyuanWuNothing/AD-RL","repo_kind":"official","path":"make_env.py","file_url":"https://github.com/QingyuanWuNothing/AD-RL/blob/HEAD/make_env.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":"af3f16c8beef0513"}},{"code_sha256_prefix":"6abe638592f2fc98","entry":"step","repo":"QingyuanWuNothing/AD-RL","repo_kind":"official","path":"DETERMINISTIC-MDP.py","file_url":"https://github.com/QingyuanWuNothing/AD-RL/blob/HEAD/DETERMINISTIC-MDP.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6abe638592f2fc98"}},{"code_sha256_prefix":"68200fece3c9d915","entry":"ReplayBuffer","repo":"qingyuanwunothing/ad-rl","repo_kind":"official","path":"AD-DQN.py","file_url":"https://github.com/qingyuanwunothing/ad-rl/blob/HEAD/AD-DQN.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":"68200fece3c9d915"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}