{"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/contrastive-explanations-for-reinforcement-2","title":"Contrastive Explanations for Reinforcement Learning via Embedded Self Predictions","arxiv_id":"2010.05180","date":"2020-10-11","proceeding":"ICLR 2021 1","authors":["Zhengxian Lin","Kim-Ho Lam","Alan Fern"],"abstract":"We investigate a deep reinforcement learning (RL) architecture that supports explaining why a learned agent prefers one action over another. The key idea is to learn action-values that are directly represented via human-understandable properties of expected futures. This is realized via the embedded self-prediction (ESP)model, which learns said properties in terms of human provided features. Action preferences can then be explained by contrasting the future properties predicted for each action. To address cases where there are a large number of features, we develop a novel method for computing minimal sufficient explanations from anESP. Our case studies in three domains, including a complex strategy game, show that ESP models can be effectively learned and support insightful explanations.","url_abs":"https://arxiv.org/abs/2010.05180v2","url_pdf":"https://arxiv.org/pdf/2010.05180v2.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":"contrastive-explanations-for-reinforcement-2","repo_url":"https://github.com/SuerpX/Embedded-Self-Predictions","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement 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":"dilated-convolution","method_name":"Dilated Convolution"},{"method_slug":"esp","method_name":"ESP"},{"method_slug":"hierarchical-feature-fusion","method_name":"Hierarchical Feature Fusion"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.05180","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.05180"}},"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/SuerpX/Embedded-Self-Predictions","reach":null}],"summary":{"ran":2,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"3e907b6fd4d68a48","entry":"_feature_model","repo":"SuerpX/Embedded-Self-Predictions","repo_kind":"official","path":"Tug-of-War/abp/models/feature_q_model.py","file_url":"https://github.com/SuerpX/Embedded-Self-Predictions/blob/HEAD/Tug-of-War/abp/models/feature_q_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3e907b6fd4d68a48"}},{"code_sha256_prefix":"553c1592f0f9b6da","entry":"_q_model","repo":"SuerpX/Embedded-Self-Predictions","repo_kind":"official","path":"Tug-of-War/abp/models/feature_q_model.py","file_url":"https://github.com/SuerpX/Embedded-Self-Predictions/blob/HEAD/Tug-of-War/abp/models/feature_q_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"553c1592f0f9b6da"}},{"code_sha256_prefix":"fab29b88af7a322e","entry":"ensure_directory_exits","repo":"SuerpX/Embedded-Self-Predictions","repo_kind":"official","path":"Tug-of-War/abp/models/feature_q_model.py","file_url":"https://github.com/SuerpX/Embedded-Self-Predictions/blob/HEAD/Tug-of-War/abp/models/feature_q_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fab29b88af7a322e"}},{"code_sha256_prefix":"ade45273ac642ffa","entry":"feature_q_model","repo":"SuerpX/Embedded-Self-Predictions","repo_kind":"official","path":"Tug-of-War/abp/models/feature_q_model.py","file_url":"https://github.com/SuerpX/Embedded-Self-Predictions/blob/HEAD/Tug-of-War/abp/models/feature_q_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ade45273ac642ffa"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}