{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/beyond-worst-case-attacks-robust-rl-with","title":"Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies","arxiv_id":"2402.12673","date":"2024-02-20","proceeding":null,"authors":["Xiangyu Liu","ChengHao Deng","Yanchao Sun","Yongyuan Liang","Furong Huang"],"abstract":"In light of the burgeoning success of reinforcement learning (RL) in diverse real-world applications, considerable focus has been directed towards ensuring RL policies are robust to adversarial attacks during test time. Current approaches largely revolve around solving a minimax problem to prepare for potential worst-case scenarios. While effective against strong attacks, these methods often compromise performance in the absence of attacks or the presence of only weak attacks. To address this, we study policy robustness under the well-accepted state-adversarial attack model, extending our focus beyond only worst-case attacks. We first formalize this task at test time as a regret minimization problem and establish its intrinsic hardness in achieving sublinear regret when the baseline policy is from a general continuous policy class, $\\Pi$. This finding prompts us to \\textit{refine} the baseline policy class $\\Pi$ prior to test time, aiming for efficient adaptation within a finite policy class $\\Tilde{\\Pi}$, which can resort to an adversarial bandit subroutine. In light of the importance of a small, finite $\\Tilde{\\Pi}$, we propose a novel training-time algorithm to iteratively discover \\textit{non-dominated policies}, forming a near-optimal and minimal $\\Tilde{\\Pi}$, thereby ensuring both robustness and test-time efficiency. Empirical validation on the Mujoco corroborates the superiority of our approach in terms of natural and robust performance, as well as adaptability to various attack scenarios.","url_abs":"https://arxiv.org/abs/2402.12673v1","url_pdf":"https://arxiv.org/pdf/2402.12673v1.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":"beyond-worst-case-attacks-robust-rl-with","repo_url":"https://github.com/umd-huang-lab/protected","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"adversarial-attack","task_name":"Adversarial Attack"},{"task_slug":"mujoco","task_name":"MuJoCo"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.12673","atlas_url":"https://app.syntology.ai/?focus=2402.12673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12673"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2402.12673"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_reference_implementation","arguments":{"name":"non-dominated policies"},"call":"get_reference_implementation(name='non-dominated policies')","min_level":{"quoted_from_server_card":["It REFUSES rather than serving below min_level, and the refusal names the highest level that exists","so lowering min_level is a deliberate, informed choice, not a guess."],"default_on_card":2,"server_card":"https://syntology.ai/.well-known/mcp/server-card.json","card_sha256":"479785a84658dd682a11b10237b3620d651d7f87799f5dc7add970aaa83f6d39","this_implementation_level":2}},{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2402.12673"},"call":"get_harvested_code_for_paper(arxiv_id=\"2402.12673\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2402.12673"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2402.12673\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2402.12673"},"call":"get_concepts_for_paper(arxiv_id=\"2402.12673\")"}],"reference_implementation":[{"method_name":"non-dominated policies","assembly_sha256":"222fad69ebfc88fe","source":"generated from the paper text (not the authors' code)","level":2,"level_is_quoted_from_server_card":[{"level":"V2","quoted":["two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs","neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)"]}],"server_card":"https://syntology.ai/.well-known/mcp/server-card.json","card_sha256":"479785a84658dd682a11b10237b3620d651d7f87799f5dc7add970aaa83f6d39","no_rung":"No rung compares this code against the authors' implementation","no_rung_quoted_from_server_card":"No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.","retrieve_with":"get_reference_implementation(name='non-dominated policies')","have_check":{"url":"https://syntology.ai/api/graph/have?x=2402.12673","call":"have('2402.12673')","in_build_sample":false}}],"reference_implementation_is":"Syntology's reference implementation of this paper's method: code Syntology generated from the paper text (not the authors' code), at the level its own end-to-end run recorded (the assembly's own level, never averaged); the level's meaning is quoted from Syntology's server card, and nothing here says the code is correct or reproduces the paper's results","by_repo":[{"repo":"umd-huang-lab/protected","kind":"official","samples":2,"ran":0,"instrument":0,"unverified":2}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","assemblies":[{"assembly_sha256":"222fad69ebfc88fe","source_kind":"generated","method_name":"non-dominated policies","realizes_method":"non-dominated policies","graph_method":"non-dominated policies","realizes_severed":false,"claim":"Compute the adversary parameter update from Algorithm 1, line 7. Given current adversary parameters nu_t (1D array of shape (D,)), the gradient of the objective with respect to nu for the new policy grad_J_new (1D array of shape (D,)), the gradient of the objective with respect to nu for the best ex","centrality":"contribution","entry":"adversary_gradient_update","entry_sha256":"eca3aa03832413107cb1c8abe3eb2d741f533b77d03101628417ef3f5fb2dfac","n_bricks":1,"bricks":[{"entry":"adversary_gradient_update","code_sha256":"eca3aa03832413107cb1c8abe3eb2d741f533b77d03101628417ef3f5fb2dfac","role":"entry","order":0,"level":2,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":null,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":true,"level":2,"against_independent_peer":true,"n_peers":1,"v3_tests_passed_both_sides":0,"means":"this assembly is a single routine, so the entry brick's verification IS the assembly's: it executed and two family-independent implementations agreed"},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"construction","claim_match_judges":["construction:spec_drafted_for_this_method"],"label_verdict":"matches","label_verdict_judged":false,"suggested_method":null,"batch_at":"2026-09-07T20:44:12+00:00","sibling_group":"2bb53090fb0f","n_siblings":0,"retention":"keep","provenance":"assembly:generated_reference_impl_v1","attached_at":"2026-09-07T20:44:12+00:00","attached_provenance":"assembly:generated_reference_impl_v1"},{"assembly_sha256":"8c539758c4e46add","source_kind":"harvested","method_name":"non-dominated policies","realizes_method":"non-dominated policies","graph_method":"non-dominated policies","realizes_severed":false,"claim":"This code implements a robust reinforcement learning method using non-dominated policies to adaptively defend against adversarial attacks during test time.","centrality":"contribution","entry":"robust_ppo_step","entry_sha256":"a41b550a8ff5fe84","n_bricks":8,"bricks":[{"entry":"robust_ppo_step","code_sha256":"a41b550a8ff5fe84","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"adv_normalize","code_sha256":"59236ac3123afcdf","role":"helper","order":1,"level":1,"status":"ran_fixture"},{"entry":"get_state_kl_bound_sgld","code_sha256":"cc9596016142c080","role":"helper","order":2,"level":1,"status":"ran_draft_wrong"},{"entry":"pack_history","code_sha256":"fe36ea6d910477c3","role":"helper","order":3,"level":1,"status":"ran_draft_wrong"},{"entry":"surrogate_reward","code_sha256":"428b336da9f35ed2","role":"loss","order":4,"level":0,"status":"unverified"},{"entry":"value_step","code_sha256":"ceb1c5e7ed63f591","role":"helper","order":5,"level":0,"status":"unverified"},{"entry":"value_loss_gae","code_sha256":"e4187dd121d7ca14","role":"loss","order":6,"level":0,"status":"unverified"},{"entry":"value_loss_returns","code_sha256":"3e4c2bb78b75b63a","role":"helper","order":7,"level":0,"status":"unverified"}],"ran_individually":3,"ran_individually_constructed":0,"ran_individually_by_status":{"ran_draft_wrong":2,"ran_fixture":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"3e3200ae268e","n_siblings":0,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"}],"assembly_sibling_groups":[{"group":"2bb53090fb0f","realizes_method":"non-dominated policies","source_kind":"generated","batch_at":"2026-09-07T20:44:12+00:00","members":["222fad69ebfc88fe"]},{"group":"3e3200ae268e","realizes_method":"non-dominated policies","source_kind":"harvested","batch_at":"2026-09-09T22:44:46+00:00","members":["8c539758c4e46add"]}],"assemblies_is":{"about":"What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results.","harvested":"assembled from code harvested from a repository linked to the paper","generated":"generated from the paper text, not the repository's code","end_to_end":"for a harvested assembly, the assembly has not been run end-to-end; for a generated one, end_to_end.level is the assembly's own level and against_independent_peer says whether it ran against a peer: an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists","bricks_level":"each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level","ran_individually":"a COUNT of bricks that ran on their own on a fixture (split by status in ran_individually_by_status), not a level; instrument statuses are failures of Syntology's instrument, not of the code","siblings":"assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another","judged":"Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as \"by construction\" or \"not judged by a model\"","level_lowered":"a generated assembly whose level Syntology's graph lowered, with the level it had, the recorded reason and when","retention":"Syntology's spending triage for further verification, not a verdict","claim_match":"the claim_match vote: IMPLEMENTS, COMPONENT or UNCLEAR. Where claim_match_basis is \"judge:<model>\", it is one model's judgement of the assembly's label against the paper's claim (claim_match_rule single_judge, the model in claim_match_judges): not a verification and not a run. Where it is \"construction\", the value was set when the code was generated for this method and no model judged it, whatever claim_match_rule says. The page prints no claim match for any assembly","label_verdict":"whether the assembly's code is the method it is labelled with: matches, cannot_tell, mislabelled (suggested_method names what it looks like instead) or not_the_method; label_verdict_judged is true only when a model read the code (claim_match_basis \"judge:<model>\")","label_verdict_judged":"where true (claim_match_basis \"judge:<model>\"), label_verdict is a single model's judgement; not calibrated; not printed on the page; where false, it was set by construction, and the page prints it unless the node is shared with another paper (node_properties_written_for)","claim":"the claim text stored on the assembly node: for a harvested assembly, what the paper claims the code implements, as the lifting model wrote it; for a generated one, the specification the code was generated from. Not verified text","centrality":"how central the lifted method is to the paper, as the lifting step recorded it: contribution, component or incidental","v3_tests_passed_both_sides":"end_to_end.v3_tests_passed_both_sides: the number of property tests derived from the paper that passed on both implementations, as the attached report lists them; a level 3 card with 0 says its report lists none","ran_individually_constructed":"ran_individually_constructed: of the bricks counted in ran_individually, how many constructed an object rather than computing a result (Syntology's RAN record's rule, read from the graph-layer sample with the brick's code_sha256); a part of ran_individually, never subtracted from it and never a failure; null where a brick that ran has no sample in the graph layer this build read, so the figure was not counted"},"assemblies_call":{"tool":"assembly","arguments":{"arxiv_id":"2402.12673"},"call":"assembly(arxiv_id=\"2402.12673\")"},"read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2402.12673.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2402.12673.svg"},"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/umd-huang-lab/protected","reach":null}],"summary":{"unverified":2},"n_samples":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":2,"ran":0,"n_ran_checked":0,"n_instrument":0,"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":2,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"samples":[{"code_sha256":"a41b550a8ff5fe84","code_sha256_prefix":"a41b550a8ff5fe84","entry":"robust_ppo_step","repo":"umd-huang-lab/protected","repo_kind":"official","path":"policy_gradients/steps.py","file_url":"https://github.com/umd-huang-lab/protected/blob/HEAD/policy_gradients/steps.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, umd-huang-lab/protected when it was checked","mcp_get_code":{"code_sha256":"a41b550a8ff5fe84"}},{"code_sha256":"ceb1c5e7ed63f591","code_sha256_prefix":"ceb1c5e7ed63f591","entry":"value_step","repo":"umd-huang-lab/protected","repo_kind":"official","path":"policy_gradients/steps.py","file_url":"https://github.com/umd-huang-lab/protected/blob/HEAD/policy_gradients/steps.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, umd-huang-lab/protected when it was checked","mcp_get_code":{"code_sha256":"ceb1c5e7ed63f591"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"686204805e3ab5e7b961c8ec5e4351e66b0a7061cf211aac7a7a5875a321508f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}