{"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/anchor-changing-regularized-natural-policy","title":"Anchor-Changing Regularized Natural Policy Gradient for Multi-Objective Reinforcement Learning","arxiv_id":"2206.05357","date":"2022-06-10","proceeding":null,"authors":["Ruida Zhou","Tao Liu","Dileep Kalathil","P. R. Kumar","Chao Tian"],"abstract":"We study policy optimization for Markov decision processes (MDPs) with multiple reward value functions, which are to be jointly optimized according to given criteria such as proportional fairness (smooth concave scalarization), hard constraints (constrained MDP), and max-min trade-off. We propose an Anchor-changing Regularized Natural Policy Gradient (ARNPG) framework, which can systematically incorporate ideas from well-performing first-order methods into the design of policy optimization algorithms for multi-objective MDP problems. Theoretically, the designed algorithms based on the ARNPG framework achieve $\\tilde{O}(1/T)$ global convergence with exact gradients. Empirically, the ARNPG-guided algorithms also demonstrate superior performance compared to some existing policy gradient-based approaches in both exact gradients and sample-based scenarios.","url_abs":"https://arxiv.org/abs/2206.05357v2","url_pdf":"https://arxiv.org/pdf/2206.05357v2.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":"anchor-changing-regularized-natural-policy","repo_url":"https://github.com/tliu1997/arnpg-morl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"anchor-changing-regularized-natural-policy","repo_url":"https://github.com/sundave1998/independent-npg-mpg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"multi-objective-reinforcement-learning","task_name":"Multi-Objective 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/2206.05357","atlas_url":"https://app.syntology.ai/?focus=2206.05357","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.05357"}},"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/tliu1997/ARNPG-MORL","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tliu1997/arnpg-morl","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sundave1998/independent-npg-mpg","reach":{"status":"ok"}}],"summary":{"ran_honours":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":"20922c79a0929bbf","entry":"flatten","repo":"tliu1997/arnpg-morl","repo_kind":"official","path":"Acrobot-v1/ARNPG-EPD_acrobot.py","file_url":"https://github.com/tliu1997/arnpg-morl/blob/HEAD/Acrobot-v1/ARNPG-EPD_acrobot.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"20922c79a0929bbf"}},{"code_sha256_prefix":"202f8338817a32ef","entry":"reward_function","repo":"tliu1997/arnpg-morl","repo_kind":"official","path":"Acrobot-v1/ARNPG-EPD_acrobot.py","file_url":"https://github.com/tliu1997/arnpg-morl/blob/HEAD/Acrobot-v1/ARNPG-EPD_acrobot.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"202f8338817a32ef"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}