{"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/solving-continuous-control-via-q-learning","title":"Solving Continuous Control via Q-learning","arxiv_id":"2210.12566","date":"2022-10-22","proceeding":null,"authors":["Tim Seyde","Peter Werner","Wilko Schwarting","Igor Gilitschenski","Martin Riedmiller","Daniela Rus","Markus Wulfmeier"],"abstract":"While there has been substantial success for solving continuous control with actor-critic methods, simpler critic-only methods such as Q-learning find limited application in the associated high-dimensional action spaces. However, most actor-critic methods come at the cost of added complexity: heuristics for stabilisation, compute requirements and wider hyperparameter search spaces. We show that a simple modification of deep Q-learning largely alleviates these issues. By combining bang-bang action discretization with value decomposition, framing single-agent control as cooperative multi-agent reinforcement learning (MARL), this simple critic-only approach matches performance of state-of-the-art continuous actor-critic methods when learning from features or pixels. We extend classical bandit examples from cooperative MARL to provide intuition for how decoupled critics leverage state information to coordinate joint optimization, and demonstrate surprisingly strong performance across a variety of continuous control tasks.","url_abs":"https://arxiv.org/abs/2210.12566v2","url_pdf":"https://arxiv.org/pdf/2210.12566v2.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":"solving-continuous-control-via-q-learning","repo_url":"https://github.com/tseyde/decqn","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"multi-agent-reinforcement-learning","task_name":"Multi-agent Reinforcement Learning"},{"task_slug":"q-learning","task_name":"Q-Learning"},{"task_slug":"continuous-control","task_name":"continuous-control"}],"methods":[{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.12566","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12566"}},"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/tseyde/decqn","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"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":"b24adadc1015ff3b","entry":"args_type","repo":"tseyde/decqn","repo_kind":"official","path":"decqn/misc/utils.py","file_url":"https://github.com/tseyde/decqn/blob/HEAD/decqn/misc/utils.py","link_basis":"harvester_set","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":"b24adadc1015ff3b"}},{"code_sha256_prefix":"4ebca99b5cc6409e","entry":"bilinear_sampler","repo":"tseyde/decqn","repo_kind":"official","path":"decqn/misc/augmentation.py","file_url":"https://github.com/tseyde/decqn/blob/HEAD/decqn/misc/augmentation.py","link_basis":"harvester_set","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":"4ebca99b5cc6409e"}},{"code_sha256_prefix":"d9ce91cb115d80d5","entry":"encode_gif","repo":"tseyde/decqn","repo_kind":"official","path":"decqn/misc/utils.py","file_url":"https://github.com/tseyde/decqn/blob/HEAD/decqn/misc/utils.py","link_basis":"harvester_set","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":"d9ce91cb115d80d5"}},{"code_sha256_prefix":"736dc8337a3505a5","entry":"get_output_dimensions","repo":"tseyde/decqn","repo_kind":"official","path":"decqn/agents/dqn/networks.py","file_url":"https://github.com/tseyde/decqn/blob/HEAD/decqn/agents/dqn/networks.py","link_basis":"harvester_set","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":"736dc8337a3505a5"}},{"code_sha256_prefix":"d4a546c4f52bf0e2","entry":"get_pixel_value","repo":"tseyde/decqn","repo_kind":"official","path":"decqn/misc/augmentation.py","file_url":"https://github.com/tseyde/decqn/blob/HEAD/decqn/misc/augmentation.py","link_basis":"harvester_set","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":"d4a546c4f52bf0e2"}},{"code_sha256_prefix":"caf0bda3e3d13202","entry":"process_config","repo":"tseyde/decqn","repo_kind":"official","path":"decqn/run_experiment.py","file_url":"https://github.com/tseyde/decqn/blob/HEAD/decqn/run_experiment.py","link_basis":"harvester_set","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":"caf0bda3e3d13202"}},{"code_sha256_prefix":"15de0471e7428ecd","entry":"random_shift","repo":"tseyde/decqn","repo_kind":"official","path":"decqn/misc/augmentation.py","file_url":"https://github.com/tseyde/decqn/blob/HEAD/decqn/misc/augmentation.py","link_basis":"harvester_set","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":"15de0471e7428ecd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}