{"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/divide-and-conquer-provably-unveiling-the","title":"Divide and Conquer: Provably Unveiling the Pareto Front with Multi-Objective Reinforcement Learning","arxiv_id":"2402.07182","date":"2024-02-11","proceeding":null,"authors":["Willem Röpke","Mathieu Reymond","Patrick Mannion","Diederik M. Roijers","Ann Nowé","Roxana Rădulescu"],"abstract":"An important challenge in multi-objective reinforcement learning is obtaining a Pareto front of policies to attain optimal performance under different preferences. We introduce Iterated Pareto Referent Optimisation (IPRO), which decomposes finding the Pareto front into a sequence of constrained single-objective problems. This enables us to guarantee convergence while providing an upper bound on the distance to undiscovered Pareto optimal solutions at each step. We evaluate IPRO using utility-based metrics and its hypervolume and find that it matches or outperforms methods that require additional assumptions. By leveraging problem-specific single-objective solvers, our approach also holds promise for applications beyond multi-objective reinforcement learning, such as planning and pathfinding.","url_abs":"https://arxiv.org/abs/2402.07182v2","url_pdf":"https://arxiv.org/pdf/2402.07182v2.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":"divide-and-conquer-provably-unveiling-the","repo_url":"https://github.com/wilrop/ipro","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"multi-objective-reinforcement-learning","task_name":"Multi-Objective Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.07182","atlas_url":"https://app.syntology.ai/?focus=2402.07182","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07182"}},"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/wilrop/ipro","reach":{"status":"ok"}}],"summary":{"ran":16,"unverified":1},"by_repo_kind":{"official":{"samples":17,"ran":16,"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":17,"samples":[{"code_sha256_prefix":"52a8f2454da4a21a","entry":"add_experiment_args","repo":"wilrop/ipro","repo_kind":"official","path":"ipro/experiments/parser.py","file_url":"https://github.com/wilrop/ipro/blob/HEAD/ipro/experiments/parser.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":"52a8f2454da4a21a"}},{"code_sha256_prefix":"3404f1fec5305aed","entry":"add_override_arg","repo":"wilrop/ipro","repo_kind":"official","path":"ipro/experiments/parser.py","file_url":"https://github.com/wilrop/ipro/blob/HEAD/ipro/experiments/parser.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":"3404f1fec5305aed"}},{"code_sha256_prefix":"143e8f13d197b27b","entry":"add_part_config_args","repo":"wilrop/ipro","repo_kind":"official","path":"ipro/experiments/parser.py","file_url":"https://github.com/wilrop/ipro/blob/HEAD/ipro/experiments/parser.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":"143e8f13d197b27b"}},{"code_sha256_prefix":"2d65ae5f69327b23","entry":"base","repo":"wilrop/ipro","repo_kind":"official","path":"ipro/utility_function/monotonic_networks.py","file_url":"https://github.com/wilrop/ipro/blob/HEAD/ipro/utility_function/monotonic_networks.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":"2d65ae5f69327b23"}},{"code_sha256_prefix":"842feee6d076f79e","entry":"base_hat","repo":"wilrop/ipro","repo_kind":"official","path":"ipro/utility_function/monotonic_networks.py","file_url":"https://github.com/wilrop/ipro/blob/HEAD/ipro/utility_function/monotonic_networks.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":"842feee6d076f79e"}},{"code_sha256_prefix":"a04d76f91bcb9475","entry":"base_tilde","repo":"wilrop/ipro","repo_kind":"official","path":"ipro/utility_function/monotonic_networks.py","file_url":"https://github.com/wilrop/ipro/blob/HEAD/ipro/utility_function/monotonic_networks.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":"a04d76f91bcb9475"}},{"code_sha256_prefix":"d5ef0b8c2e836d13","entry":"compress_dataset","repo":"wilrop/ipro","repo_kind":"official","path":"ipro/analysis/visualise.py","file_url":"https://github.com/wilrop/ipro/blob/HEAD/ipro/analysis/visualise.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":"d5ef0b8c2e836d13"}},{"code_sha256_prefix":"777cfa6dd1fb1f27","entry":"generate_problem","repo":"wilrop/ipro","repo_kind":"official","path":"ipro/experiments/known_problem.py","file_url":"https://github.com/wilrop/ipro/blob/HEAD/ipro/experiments/known_problem.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":"777cfa6dd1fb1f27"}},{"code_sha256_prefix":"3679b98747532498","entry":"get_bounding_box","repo":"wilrop/ipro","repo_kind":"official","path":"ipro/environments/bounding_boxes.py","file_url":"https://github.com/wilrop/ipro/blob/HEAD/ipro/environments/bounding_boxes.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":"3679b98747532498"}},{"code_sha256_prefix":"704ed59871f125a2","entry":"load_config","repo":"wilrop/ipro","repo_kind":"official","path":"ipro/experiments/load_config.py","file_url":"https://github.com/wilrop/ipro/blob/HEAD/ipro/experiments/load_config.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":"704ed59871f125a2"}},{"code_sha256_prefix":"c6475c884ae6f1a4","entry":"load_parts","repo":"wilrop/ipro","repo_kind":"official","path":"ipro/experiments/load_config.py","file_url":"https://github.com/wilrop/ipro/blob/HEAD/ipro/experiments/load_config.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":"c6475c884ae6f1a4"}},{"code_sha256_prefix":"80c55202071c8a6f","entry":"read_data","repo":"wilrop/ipro","repo_kind":"official","path":"ipro/analysis/visualise.py","file_url":"https://github.com/wilrop/ipro/blob/HEAD/ipro/analysis/visualise.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":"80c55202071c8a6f"}},{"code_sha256_prefix":"ea31113d66514a24","entry":"remove_unused_params","repo":"wilrop/ipro","repo_kind":"official","path":"ipro/experiments/reproduce_experiment.py","file_url":"https://github.com/wilrop/ipro/blob/HEAD/ipro/experiments/reproduce_experiment.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":"ea31113d66514a24"}},{"code_sha256_prefix":"c2ac7d83c99ad669","entry":"scale","repo":"wilrop/ipro","repo_kind":"official","path":"ipro/analysis/compute_metrics.py","file_url":"https://github.com/wilrop/ipro/blob/HEAD/ipro/analysis/compute_metrics.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":"c2ac7d83c99ad669"}},{"code_sha256_prefix":"bbbd14a92aa4ba03","entry":"setup_config","repo":"wilrop/ipro","repo_kind":"official","path":"ipro/experiments/reproduce_experiment.py","file_url":"https://github.com/wilrop/ipro/blob/HEAD/ipro/experiments/reproduce_experiment.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":"bbbd14a92aa4ba03"}},{"code_sha256_prefix":"a385006079999dcf","entry":"setup_outer_params","repo":"wilrop/ipro","repo_kind":"official","path":"ipro/experiments/reproduce_experiment.py","file_url":"https://github.com/wilrop/ipro/blob/HEAD/ipro/experiments/reproduce_experiment.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":"a385006079999dcf"}},{"code_sha256_prefix":"13c3fb149d563ee2","entry":"override_config","repo":"wilrop/ipro","repo_kind":"official","path":"ipro/experiments/load_config.py","file_url":"https://github.com/wilrop/ipro/blob/HEAD/ipro/experiments/load_config.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":"13c3fb149d563ee2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}