{"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/quantum-reinforcement-learning","title":"Quantum reinforcement learning","arxiv_id":"0810.3828","date":"2008-10-21","proceeding":null,"authors":["Daoyi Dong","Chunlin Chen","Hanxiong Li","Tzyh-Jong Tarn"],"abstract":"The key approaches for machine learning, especially learning in unknown\nprobabilistic environments are new representations and computation mechanisms.\nIn this paper, a novel quantum reinforcement learning (QRL) method is proposed\nby combining quantum theory and reinforcement learning (RL). Inspired by the\nstate superposition principle and quantum parallelism, a framework of value\nupdating algorithm is introduced. The state (action) in traditional RL is\nidentified as the eigen state (eigen action) in QRL. The state (action) set can\nbe represented with a quantum superposition state and the eigen state (eigen\naction) can be obtained by randomly observing the simulated quantum state\naccording to the collapse postulate of quantum measurement. The probability of\nthe eigen action is determined by the probability amplitude, which is\nparallelly updated according to rewards. Some related characteristics of QRL\nsuch as convergence, optimality and balancing between exploration and\nexploitation are also analyzed, which shows that this approach makes a good\ntradeoff between exploration and exploitation using the probability amplitude\nand can speed up learning through the quantum parallelism. To evaluate the\nperformance and practicability of QRL, several simulated experiments are given\nand the results demonstrate the effectiveness and superiority of QRL algorithm\nfor some complex problems. The present work is also an effective exploration on\nthe application of quantum computation to artificial intelligence.","url_abs":"http://arxiv.org/abs/0810.3828v1","url_pdf":"http://arxiv.org/pdf/0810.3828v1.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":"quantum-reinforcement-learning","repo_url":"https://github.com/LauraGentini/QRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"quantum-reinforcement-learning","repo_url":"https://github.com/milesgep/Quantum-Reinforcement-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"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":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=0810.3828","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"0810.3828"}},"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/LauraGentini/QRL","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/milesgep/Quantum-Reinforcement-Learning","reach":null}],"summary":{"ran_honours":2,"ran_fixture":1},"by_repo_kind":{"listed":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"5eb058526a1db467","entry":"atari_make_initial_state","repo":"milesgep/Quantum-Reinforcement-Learning","repo_kind":"listed","path":"lib/atari/helpers.py","file_url":"https://github.com/milesgep/Quantum-Reinforcement-Learning/blob/HEAD/lib/atari/helpers.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5eb058526a1db467"}},{"code_sha256_prefix":"ae6f0c054365a141","entry":"atari_make_next_state","repo":"milesgep/Quantum-Reinforcement-Learning","repo_kind":"listed","path":"lib/atari/helpers.py","file_url":"https://github.com/milesgep/Quantum-Reinforcement-Learning/blob/HEAD/lib/atari/helpers.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ae6f0c054365a141"}},{"code_sha256_prefix":"ef64cd39233ab328","entry":"collapseActionSelectionMethod","repo":"milesgep/Quantum-Reinforcement-Learning","repo_kind":"listed","path":"quantumCliffWalker.py","file_url":"https://github.com/milesgep/Quantum-Reinforcement-Learning/blob/HEAD/quantumCliffWalker.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ef64cd39233ab328"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}