{"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/twice-regularized-mdps-and-the-equivalence","title":"Twice regularized MDPs and the equivalence between robustness and regularization","arxiv_id":"2110.06267","date":"2021-10-12","proceeding":"NeurIPS 2021 12","authors":["Esther Derman","Matthieu Geist","Shie Mannor"],"abstract":"Robust Markov decision processes (MDPs) aim to handle changing or partially known system dynamics. To solve them, one typically resorts to robust optimization methods. However, this significantly increases computational complexity and limits scalability in both learning and planning. On the other hand, regularized MDPs show more stability in policy learning without impairing time complexity. Yet, they generally do not encompass uncertainty in the model dynamics. In this work, we aim to learn robust MDPs using regularization. We first show that regularized MDPs are a particular instance of robust MDPs with uncertain reward. We thus establish that policy iteration on reward-robust MDPs can have the same time complexity as on regularized MDPs. We further extend this relationship to MDPs with uncertain transitions: this leads to a regularization term with an additional dependence on the value function. We finally generalize regularized MDPs to twice regularized MDPs (R${}^2$ MDPs), i.e., MDPs with $\\textit{both}$ value and policy regularization. The corresponding Bellman operators enable developing policy iteration schemes with convergence and robustness guarantees. It also reduces planning and learning in robust MDPs to regularized MDPs.","url_abs":"https://arxiv.org/abs/2110.06267v1","url_pdf":"https://arxiv.org/pdf/2110.06267v1.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":[],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.06267","atlas_url":"https://app.syntology.ai/?focus=2110.06267","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06267"}},"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/EstherDerman/r2mdp","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"found_in_text":{"samples":4,"ran":1,"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":"6ab90d189238f3d1","entry":"modified_policy_iteration","repo":"EstherDerman/r2mdp","repo_kind":"found_in_text","path":"planning.py","file_url":"https://github.com/EstherDerman/r2mdp/blob/HEAD/planning.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6ab90d189238f3d1"}},{"code_sha256_prefix":"7b31df75c68262d4","entry":"policy_eval","repo":"EstherDerman/r2mdp","repo_kind":"found_in_text","path":"planning.py","file_url":"https://github.com/EstherDerman/r2mdp/blob/HEAD/planning.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":"7b31df75c68262d4"}},{"code_sha256_prefix":"7dd83bae6f28cf1d","entry":"reg_modified_policy_iteration","repo":"EstherDerman/r2mdp","repo_kind":"found_in_text","path":"reg_planning.py","file_url":"https://github.com/EstherDerman/r2mdp/blob/HEAD/reg_planning.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":"7dd83bae6f28cf1d"}},{"code_sha256_prefix":"5d91189e75c41963","entry":"reg_policy_eval","repo":"EstherDerman/r2mdp","repo_kind":"found_in_text","path":"reg_planning.py","file_url":"https://github.com/EstherDerman/r2mdp/blob/HEAD/reg_planning.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":"5d91189e75c41963"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}