{"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/dropout-q-functions-for-doubly-efficient","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","arxiv_id":"2110.02034","date":"2021-10-05","proceeding":"ICLR 2022 4","authors":["Takuya Hiraoka","Takahisa Imagawa","Taisei Hashimoto","Takashi Onishi","Yoshimasa Tsuruoka"],"abstract":"Randomized ensembled double Q-learning (REDQ) (Chen et al., 2021b) has recently achieved state-of-the-art sample efficiency on continuous-action reinforcement learning benchmarks. This superior sample efficiency is made possible by using a large Q-function ensemble. However, REDQ is much less computationally efficient than non-ensemble counterparts such as Soft Actor-Critic (SAC) (Haarnoja et al., 2018a). To make REDQ more computationally efficient, we propose a method of improving computational efficiency called DroQ, which is a variant of REDQ that uses a small ensemble of dropout Q-functions. Our dropout Q-functions are simple Q-functions equipped with dropout connection and layer normalization. Despite its simplicity of implementation, our experimental results indicate that DroQ is doubly (sample and computationally) efficient. It achieved comparable sample efficiency with REDQ, much better computational efficiency than REDQ, and comparable computational efficiency with that of SAC.","url_abs":"https://arxiv.org/abs/2110.02034v2","url_pdf":"https://arxiv.org/pdf/2110.02034v2.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":"dropout-q-functions-for-doubly-efficient","repo_url":"https://github.com/TakuyaHiraoka/Dropout-Q-Functions-for-Doubly-Efficient-Reinforcement-Learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"dropout-q-functions-for-doubly-efficient","repo_url":"https://github.com/araffin/sbx","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"q-learning","task_name":"Q-Learning"},{"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":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dilated-convolution","method_name":"Dilated Convolution"},{"method_slug":"double-q-learning","method_name":"Double Q-learning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"q-learning","method_name":"Q-Learning"},{"method_slug":"sac","method_name":"SAC"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2110.02034","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.02034"}},"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/ku2482/soft-actor-critic.pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/watchernyu/REDQ","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TakuyaHiraoka/Dropout-Q-Functions-for-Doubly-Efficient-Reinforcement-Learning","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/araffin/sbx","reach":null}],"summary":{"ran":4,"ran_honours":2,"unverified":2},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"found_in_text":{"samples":7,"ran":5,"repositories":2}},"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":"3ec1489c1ccfeec3","entry":"Mlp","repo":"watchernyu/REDQ","repo_kind":"found_in_text","path":"redq/algos/redq_sac.py","file_url":"https://github.com/watchernyu/REDQ/blob/HEAD/redq/algos/redq_sac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ec1489c1ccfeec3"}},{"code_sha256_prefix":"820da6f0b914ce98","entry":"ReplayBuffer","repo":"watchernyu/REDQ","repo_kind":"found_in_text","path":"redq/algos/redq_sac.py","file_url":"https://github.com/watchernyu/REDQ/blob/HEAD/redq/algos/redq_sac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"820da6f0b914ce98"}},{"code_sha256_prefix":"5fb36a006ce8ed7c","entry":"TanhGaussianPolicy","repo":"watchernyu/REDQ","repo_kind":"found_in_text","path":"redq/algos/redq_sac.py","file_url":"https://github.com/watchernyu/REDQ/blob/HEAD/redq/algos/redq_sac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5fb36a006ce8ed7c"}},{"code_sha256_prefix":"dfde273b47c42786","entry":"get_probabilistic_num_min","repo":"watchernyu/REDQ","repo_kind":"found_in_text","path":"redq/algos/redq_sac.py","file_url":"https://github.com/watchernyu/REDQ/blob/HEAD/redq/algos/redq_sac.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dfde273b47c42786"}},{"code_sha256_prefix":"88623398df64361e","entry":"test_agent","repo":"takuyahiraoka/dropout-q-functions-for-doubly-efficient-reinforcement-learning","repo_kind":"official","path":"OriginalREDQCodebase/redq/algos/core.py","file_url":"https://github.com/takuyahiraoka/dropout-q-functions-for-doubly-efficient-reinforcement-learning/blob/HEAD/OriginalREDQCodebase/redq/algos/core.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"88623398df64361e"}},{"code_sha256_prefix":"3afd917c65b80e08","entry":"to_batch","repo":"ku2482/soft-actor-critic.pytorch","repo_kind":"found_in_text","path":"code/utils.py","file_url":"https://github.com/ku2482/soft-actor-critic.pytorch/blob/HEAD/code/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3afd917c65b80e08"}},{"code_sha256_prefix":"c122b3cd8b4c6346","entry":"REDQSACAgent","repo":"watchernyu/REDQ","repo_kind":"found_in_text","path":"redq/algos/redq_sac.py","file_url":"https://github.com/watchernyu/REDQ/blob/HEAD/redq/algos/redq_sac.py","link_basis":"first_harvest_node","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":"c122b3cd8b4c6346"}},{"code_sha256_prefix":"f95d746979ff7da6","entry":"soft_update_model1_with_model2","repo":"watchernyu/REDQ","repo_kind":"found_in_text","path":"redq/algos/redq_sac.py","file_url":"https://github.com/watchernyu/REDQ/blob/HEAD/redq/algos/redq_sac.py","link_basis":"first_harvest_node","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":"f95d746979ff7da6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}