{"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/discriminative-deep-dyna-q-robust-planning","title":"Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning","arxiv_id":"1808.09442","date":"2018-08-28","proceeding":"EMNLP 2018 10","authors":["Shang-Yu Su","Xiujun Li","Jianfeng Gao","Jingjing Liu","Yun-Nung Chen"],"abstract":"This paper presents a Discriminative Deep Dyna-Q (D3Q) approach to improving\nthe effectiveness and robustness of Deep Dyna-Q (DDQ), a recently proposed\nframework that extends the Dyna-Q algorithm to integrate planning for\ntask-completion dialogue policy learning. To obviate DDQ's high dependency on\nthe quality of simulated experiences, we incorporate an RNN-based discriminator\nin D3Q to differentiate simulated experience from real user experience in order\nto control the quality of training data. Experiments show that D3Q\nsignificantly outperforms DDQ by controlling the quality of simulated\nexperience used for planning. The effectiveness and robustness of D3Q is\nfurther demonstrated in a domain extension setting, where the agent's\ncapability of adapting to a changing environment is tested.","url_abs":"http://arxiv.org/abs/1808.09442v2","url_pdf":"http://arxiv.org/pdf/1808.09442v2.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":"discriminative-deep-dyna-q-robust-planning","repo_url":"https://github.com/MiuLab/D3Q","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"discriminative-deep-dyna-q-robust-planning","repo_url":"https://github.com/Yuqing2018/D3Q_Python3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"discriminative-deep-dyna-q-robust-planning","repo_url":"https://github.com/loremdai/Duelling_D3Q","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}}],"tasks":[{"task_slug":"task-completion-dialogue-policy-learning","task_name":"Task-Completion Dialogue Policy Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.09442","atlas_url":"https://app.syntology.ai/?focus=1808.09442","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.09442"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/loremdai/Duelling_D3Q","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MiuLab/D3Q","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Yuqing2018/D3Q_Python3","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":3,"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":"a97a8e0856ccb2bc","entry":"draw","repo":"Yuqing2018/D3Q_Python3","repo_kind":"listed","path":"D3Q/src/draw_figure.py","file_url":"https://github.com/Yuqing2018/D3Q_Python3/blob/HEAD/D3Q/src/draw_figure.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":"a97a8e0856ccb2bc"}},{"code_sha256_prefix":"49f5c7b0ffd86759","entry":"read_performance","repo":"Yuqing2018/D3Q_Python3","repo_kind":"listed","path":"D3Q/src/draw_figure.py","file_url":"https://github.com/Yuqing2018/D3Q_Python3/blob/HEAD/D3Q/src/draw_figure.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":"49f5c7b0ffd86759"}},{"code_sha256_prefix":"8a8a9a5bf7ce2f6d","entry":"show_model_performance","repo":"Yuqing2018/D3Q_Python3","repo_kind":"listed","path":"D3Q/src/draw_figure.py","file_url":"https://github.com/Yuqing2018/D3Q_Python3/blob/HEAD/D3Q/src/draw_figure.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":"8a8a9a5bf7ce2f6d"}},{"code_sha256_prefix":"5e4fd7cf91f440fc","entry":"text_to_dict","repo":"MiuLab/D3Q","repo_kind":"official","path":"D3Q/src/deep_dialog/dialog_system/dict_reader.py","file_url":"https://github.com/MiuLab/D3Q/blob/HEAD/D3Q/src/deep_dialog/dialog_system/dict_reader.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":"5e4fd7cf91f440fc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}