{"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/self-supervised-discovering-of-causal","title":"Self-Supervised Discovering of Interpretable Features for Reinforcement Learning","arxiv_id":"2003.07069","date":"2020-03-16","proceeding":null,"authors":["Wenjie Shi","Gao Huang","Shiji Song","Zhuoyuan Wang","Tingyu Lin","Cheng Wu"],"abstract":"Deep reinforcement learning (RL) has recently led to many breakthroughs on a range of complex control tasks. However, the agent's decision-making process is generally not transparent. The lack of interpretability hinders the applicability of RL in safety-critical scenarios. While several methods have attempted to interpret vision-based RL, most come without detailed explanation for the agent's behavior. In this paper, we propose a self-supervised interpretable framework, which can discover interpretable features to enable easy understanding of RL agents even for non-experts. Specifically, a self-supervised interpretable network (SSINet) is employed to produce fine-grained attention masks for highlighting task-relevant information, which constitutes most evidence for the agent's decisions. We verify and evaluate our method on several Atari 2600 games as well as Duckietown, which is a challenging self-driving car simulator environment. The results show that our method renders empirical evidences about how the agent makes decisions and why the agent performs well or badly, especially when transferred to novel scenes. Overall, our method provides valuable insight into the internal decision-making process of vision-based RL. In addition, our method does not use any external labelled data, and thus demonstrates the possibility to learn high-quality mask through a self-supervised manner, which may shed light on new paradigms for label-free vision learning such as self-supervised segmentation and detection.","url_abs":"https://arxiv.org/abs/2003.07069v4","url_pdf":"https://arxiv.org/pdf/2003.07069v4.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":"self-supervised-discovering-of-causal","repo_url":"https://github.com/shiwj16/SSINet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"decision-making","task_name":"Decision Making"},{"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":"interpretability","method_name":"Interpretability"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2003.07069","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.07069"}},"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/shiwj16/SSINet","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":4,"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":6,"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":"f14815b1ec63be18","entry":"batchnorm","repo":"shiwj16/SSINet","repo_kind":"official","path":"net_parts/refinenetLW_parts.py","file_url":"https://github.com/shiwj16/SSINet/blob/HEAD/net_parts/refinenetLW_parts.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f14815b1ec63be18"}},{"code_sha256_prefix":"9d5555c9ff725b7f","entry":"center_crop","repo":"shiwj16/SSINet","repo_kind":"official","path":"net_parts/fcdensenet_parts.py","file_url":"https://github.com/shiwj16/SSINet/blob/HEAD/net_parts/fcdensenet_parts.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":"9d5555c9ff725b7f"}},{"code_sha256_prefix":"bc359191fdd6e179","entry":"conv3x3","repo":"shiwj16/SSINet","repo_kind":"official","path":"net_parts/refinenetLW_parts.py","file_url":"https://github.com/shiwj16/SSINet/blob/HEAD/net_parts/refinenetLW_parts.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bc359191fdd6e179"}},{"code_sha256_prefix":"ca099495da934438","entry":"make_layer","repo":"shiwj16/SSINet","repo_kind":"official","path":"net_parts/deeplabv3_parts.py","file_url":"https://github.com/shiwj16/SSINet/blob/HEAD/net_parts/deeplabv3_parts.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ca099495da934438"}},{"code_sha256_prefix":"96708b203eb62ef3","entry":"normalized_columns_initializer","repo":"shiwj16/SSINet","repo_kind":"official","path":"src/networks.py","file_url":"https://github.com/shiwj16/SSINet/blob/HEAD/src/networks.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"96708b203eb62ef3"}},{"code_sha256_prefix":"91a91c0edd5005d4","entry":"conv1x1","repo":"shiwj16/SSINet","repo_kind":"official","path":"net_parts/refinenetLW_parts.py","file_url":"https://github.com/shiwj16/SSINet/blob/HEAD/net_parts/refinenetLW_parts.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":"91a91c0edd5005d4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}