{"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/interpretable-concept-bottlenecks-to-align","title":"Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents","arxiv_id":"2401.05821","date":"2024-01-11","proceeding":null,"authors":["Quentin Delfosse","Sebastian Sztwiertnia","Mark Rothermel","Wolfgang Stammer","Kristian Kersting"],"abstract":"Goal misalignment, reward sparsity and difficult credit assignment are only a few of the many issues that make it difficult for deep reinforcement learning (RL) agents to learn optimal policies. Unfortunately, the black-box nature of deep neural networks impedes the inclusion of domain experts for inspecting the model and revising suboptimal policies. To this end, we introduce *Successive Concept Bottleneck Agents* (SCoBots), that integrate consecutive concept bottleneck (CB) layers. In contrast to current CB models, SCoBots do not just represent concepts as properties of individual objects, but also as relations between objects which is crucial for many RL tasks. Our experimental results provide evidence of SCoBots' competitive performances, but also of their potential for domain experts to understand and regularize their behavior. Among other things, SCoBots enabled us to identify a previously unknown misalignment problem in the iconic video game, Pong, and resolve it. Overall, SCoBots thus result in more human-aligned RL agents. Our code is available at https://github.com/k4ntz/SCoBots .","url_abs":"https://arxiv.org/abs/2401.05821v4","url_pdf":"https://arxiv.org/pdf/2401.05821v4.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":"interpretable-concept-bottlenecks-to-align","repo_url":"https://github.com/k4ntz/scobots","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2401.05821","atlas_url":"https://app.syntology.ai/?focus=2401.05821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05821"}},"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/k4ntz/scobots","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"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":"2c6d19c5c676e4ec","entry":"extract_tree_body_as_code","repo":"k4ntz/scobots","repo_kind":"official","path":"utils/tree_visualizer.py","file_url":"https://github.com/k4ntz/scobots/blob/HEAD/utils/tree_visualizer.py","link_basis":"first_harvest_node","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":"2c6d19c5c676e4ec"}},{"code_sha256_prefix":"f01a25917320dad0","entry":"find_focus_file","repo":"k4ntz/scobots","repo_kind":"official","path":"utils/tree_visualizer.py","file_url":"https://github.com/k4ntz/scobots/blob/HEAD/utils/tree_visualizer.py","link_basis":"first_harvest_node","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":"f01a25917320dad0"}},{"code_sha256_prefix":"c016b9dcd96f3eec","entry":"flist","repo":"k4ntz/scobots","repo_kind":"official","path":"render_agent.py","file_url":"https://github.com/k4ntz/scobots/blob/HEAD/render_agent.py","link_basis":"first_harvest_node","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":"c016b9dcd96f3eec"}},{"code_sha256_prefix":"1a85bbda0f2c2ec6","entry":"format_feature","repo":"k4ntz/scobots","repo_kind":"official","path":"scobi/core.py","file_url":"https://github.com/k4ntz/scobots/blob/HEAD/scobi/core.py","link_basis":"first_harvest_node","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":"1a85bbda0f2c2ec6"}},{"code_sha256_prefix":"9af3c5d5d1cd46b9","entry":"format_text","repo":"k4ntz/scobots","repo_kind":"official","path":"paper_experiments/results/display_results.py","file_url":"https://github.com/k4ntz/scobots/blob/HEAD/paper_experiments/results/display_results.py","link_basis":"first_harvest_node","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":"9af3c5d5d1cd46b9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}