{"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/fantastic-rewards-and-how-to-tame-them-a-case","title":"Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems","arxiv_id":"2302.10342","date":"2023-02-20","proceeding":null,"authors":["Yihao Feng","Shentao Yang","Shujian Zhang","JianGuo Zhang","Caiming Xiong","Mingyuan Zhou","Huan Wang"],"abstract":"When learning task-oriented dialogue (ToD) agents, reinforcement learning (RL) techniques can naturally be utilized to train dialogue strategies to achieve user-specific goals. Prior works mainly focus on adopting advanced RL techniques to train the ToD agents, while the design of the reward function is not well studied. This paper aims at answering the question of how to efficiently learn and leverage a reward function for training end-to-end (E2E) ToD agents. Specifically, we introduce two generalized objectives for reward-function learning, inspired by the classical learning-to-rank literature. Further, we utilize the learned reward function to guide the training of the E2E ToD agent. With the proposed techniques, we achieve competitive results on the E2E response-generation task on the Multiwoz 2.0 dataset. Source code and checkpoints are publicly released at https://github.com/Shentao-YANG/Fantastic_Reward_ICLR2023.","url_abs":"https://arxiv.org/abs/2302.10342v1","url_pdf":"https://arxiv.org/pdf/2302.10342v1.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":"fantastic-rewards-and-how-to-tame-them-a-case","repo_url":"https://github.com/budzianowski/multiwoz","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"fantastic-rewards-and-how-to-tame-them-a-case","repo_url":"https://github.com/shentao-yang/fantastic_reward_iclr2023","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"learning-to-rank","task_name":"Learning-To-Rank"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"response-generation","task_name":"Response Generation"},{"task_slug":"task-oriented-dialogue-systems","task_name":"Task-Oriented Dialogue Systems"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2302.10342","atlas_url":"https://app.syntology.ai/?focus=2302.10342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.10342"}},"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":"deterministic:regex_extraction","url":"https://github.com/Shentao-YANG/Fantastic","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shentao-yang/fantastic_reward_iclr2023","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/budzianowski/multiwoz","reach":null}],"summary":{"ran":4,"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":11,"ran":5,"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":"c1f35d36da13f065","entry":"binaryTupleList2Tensor","repo":"shentao-yang/fantastic_reward_iclr2023","repo_kind":"official","path":"RewardTorch.py","file_url":"https://github.com/shentao-yang/fantastic_reward_iclr2023/blob/HEAD/RewardTorch.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":"c1f35d36da13f065"}},{"code_sha256_prefix":"b849278a0ba6c25c","entry":"cuda_","repo":"shentao-yang/fantastic_reward_iclr2023","repo_kind":"official","path":"BART.py","file_url":"https://github.com/shentao-yang/fantastic_reward_iclr2023/blob/HEAD/BART.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b849278a0ba6c25c"}},{"code_sha256_prefix":"7f76b00aa1bb20bf","entry":"get_state","repo":"shentao-yang/fantastic_reward_iclr2023","repo_kind":"official","path":"EstimateBehaviorPolicy.py","file_url":"https://github.com/shentao-yang/fantastic_reward_iclr2023/blob/HEAD/EstimateBehaviorPolicy.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":"7f76b00aa1bb20bf"}},{"code_sha256_prefix":"9f2a9615de6e84bd","entry":"get_turn_state","repo":"shentao-yang/fantastic_reward_iclr2023","repo_kind":"official","path":"EstimateBehaviorPolicy.py","file_url":"https://github.com/shentao-yang/fantastic_reward_iclr2023/blob/HEAD/EstimateBehaviorPolicy.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f2a9615de6e84bd"}},{"code_sha256_prefix":"e00ccf7847d12b59","entry":"shift_tokens_right","repo":"shentao-yang/fantastic_reward_iclr2023","repo_kind":"official","path":"BART.py","file_url":"https://github.com/shentao-yang/fantastic_reward_iclr2023/blob/HEAD/BART.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e00ccf7847d12b59"}},{"code_sha256_prefix":"4c62f23ce8135bda","entry":"clean_time","repo":"shentao-yang/fantastic_reward_iclr2023","repo_kind":"official","path":"damd_multiwoz/clean_dataset.py","file_url":"https://github.com/shentao-yang/fantastic_reward_iclr2023/blob/HEAD/damd_multiwoz/clean_dataset.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":"4c62f23ce8135bda"}},{"code_sha256_prefix":"a3f6d589f208358b","entry":"get_state_act","repo":"shentao-yang/fantastic_reward_iclr2023","repo_kind":"official","path":"EstimateBehaviorPolicy.py","file_url":"https://github.com/shentao-yang/fantastic_reward_iclr2023/blob/HEAD/EstimateBehaviorPolicy.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":"a3f6d589f208358b"}},{"code_sha256_prefix":"c9f6adbecd206460","entry":"invert_mask","repo":"shentao-yang/fantastic_reward_iclr2023","repo_kind":"official","path":"BART.py","file_url":"https://github.com/shentao-yang/fantastic_reward_iclr2023/blob/HEAD/BART.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":"c9f6adbecd206460"}},{"code_sha256_prefix":"54302690d7f170c5","entry":"numpy2torch","repo":"shentao-yang/fantastic_reward_iclr2023","repo_kind":"official","path":"RewardTorch.py","file_url":"https://github.com/shentao-yang/fantastic_reward_iclr2023/blob/HEAD/RewardTorch.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":"54302690d7f170c5"}},{"code_sha256_prefix":"ef7fddf0c4145890","entry":"numpyBinaryTuple2torch","repo":"shentao-yang/fantastic_reward_iclr2023","repo_kind":"official","path":"RewardTorch.py","file_url":"https://github.com/shentao-yang/fantastic_reward_iclr2023/blob/HEAD/RewardTorch.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":"ef7fddf0c4145890"}},{"code_sha256_prefix":"a9b8c7a10994073f","entry":"puntuation_handler","repo":"shentao-yang/fantastic_reward_iclr2023","repo_kind":"official","path":"utils.py","file_url":"https://github.com/shentao-yang/fantastic_reward_iclr2023/blob/HEAD/utils.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":"a9b8c7a10994073f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}