{"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/randomized-ensembled-double-q-learning-1","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","arxiv_id":"2101.05982","date":"2021-01-15","proceeding":"ICLR 2021 1","authors":["Xinyue Chen","Che Wang","Zijian Zhou","Keith Ross"],"abstract":"Using a high Update-To-Data (UTD) ratio, model-based methods have recently achieved much higher sample efficiency than previous model-free methods for continuous-action DRL benchmarks. In this paper, we introduce a simple model-free algorithm, Randomized Ensembled Double Q-Learning (REDQ), and show that its performance is just as good as, if not better than, a state-of-the-art model-based algorithm for the MuJoCo benchmark. Moreover, REDQ can achieve this performance using fewer parameters than the model-based method, and with less wall-clock run time. REDQ has three carefully integrated ingredients which allow it to achieve its high performance: (i) a UTD ratio >> 1; (ii) an ensemble of Q functions; (iii) in-target minimization across a random subset of Q functions from the ensemble. Through carefully designed experiments, we provide a detailed analysis of REDQ and related model-free algorithms. To our knowledge, REDQ is the first successful model-free DRL algorithm for continuous-action spaces using a UTD ratio >> 1.","url_abs":"https://arxiv.org/abs/2101.05982v2","url_pdf":"https://arxiv.org/pdf/2101.05982v2.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":"randomized-ensembled-double-q-learning-1","repo_url":"https://github.com/watchernyu/REDQ","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"randomized-ensembled-double-q-learning-1","repo_url":"https://github.com/LucasAlegre/sac-plus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"randomized-ensembled-double-q-learning-1","repo_url":"https://github.com/trackmania-rl/tmrl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"randomized-ensembled-double-q-learning-1","repo_url":"https://github.com/ustcmike/adaeq_neurips21","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"randomized-ensembled-double-q-learning-1","repo_url":"https://github.com/BY571/Randomized-Ensembled-Double-Q-learning-REDQ-","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"randomized-ensembled-double-q-learning-1","repo_url":"https://github.com/facebookresearch/rl/tree/main/examples/redq/redq.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null}],"tasks":[{"task_slug":"mujoco","task_name":"MuJoCo"},{"task_slug":"q-learning","task_name":"Q-Learning"}],"methods":[{"method_slug":"double-q-learning","method_name":"Double Q-learning"},{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2101.05982","atlas_url":"https://app.syntology.ai/?focus=2101.05982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.05982"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2101.05982"},"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":"Randomized Ensembled Double Q-Learning (REDQ)"},"call":"get_reference_implementation(name='Randomized Ensembled Double Q-Learning (REDQ)')","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":3}},{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2101.05982"},"call":"get_harvested_code_for_paper(arxiv_id=\"2101.05982\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2101.05982"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2101.05982\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2101.05982"},"call":"get_concepts_for_paper(arxiv_id=\"2101.05982\")"}],"reference_implementation":[{"method_name":"Randomized Ensembled Double Q-Learning (REDQ)","assembly_sha256":"8b0063c84f086407","source":"generated from the paper text (not the authors' code)","level":3,"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)"]},{"level":"V3","quoted":["paper-derived property tests pass on both of those same two generations."]}],"server_card":"https://syntology.ai/.well-known/mcp/server-card.json","card_sha256":"479785a84658dd682a11b10237b3620d651d7f87799f5dc7add970aaa83f6d39","v3_tests_passed_both_sides":0,"level_3_note":"level 3 is recorded, but its report lists no property test that passed on both","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='Randomized Ensembled Double Q-Learning (REDQ)')","have_check":{"url":"https://syntology.ai/api/graph/have?x=2101.05982","call":"have('2101.05982')","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":"watchernyu/REDQ","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2110.02034"],"harvested_for_calls":[{"arxiv_id":"2110.02034","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2110.02034"},"call":"get_harvested_code_for_paper(arxiv_id=\"2110.02034\")"}]},{"repo":"LucasAlegre/sac-plus","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"trackmania-rl/tmrl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ustcmike/adaeq_neurips21","kind":"listed","samples":2,"ran":1,"instrument":0,"unverified":1},{"repo":"BY571/Randomized-Ensembled-Double-Q-learning-REDQ-","kind":"listed","samples":3,"ran":3,"instrument":0,"unverified":0},{"repo":"facebookresearch/rl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2306.17100"],"harvested_for_calls":[{"arxiv_id":"2306.17100","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2306.17100"},"call":"get_harvested_code_for_paper(arxiv_id=\"2306.17100\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"8b0063c84f086407","source_kind":"generated","method_name":"Randomized Ensembled Double Q-Learning (REDQ)","realizes_method":"Randomized Ensembled Double Q-Learning (REDQ)","graph_method":"Randomized Ensembled Double Q-Learning (REDQ)","realizes_severed":false,"claim":"Compute the REDQ Q-learning target for a batch of transitions.\n\nInputs:\n- rewards: shape (batch_size,) array of scalar rewards r\n- next_q_values: shape (batch_size, M) array where next_q_values[b, i] is the Q-value Q_{phi_targ,i}(s', a') for the b-th transition, evaluated at next state s' and sample","centrality":"contribution","entry":"redq_q_target","entry_sha256":"c9a0630f1186534d8cc4ecdd96c5eb09e67cb50c08b9b806a16372562d904154","n_bricks":1,"bricks":[{"entry":"redq_q_target","code_sha256":"c9a0630f1186534d8cc4ecdd96c5eb09e67cb50c08b9b806a16372562d904154","role":"entry","order":0,"level":3,"status":"ran_honours"}],"ran_individually":1,"ran_individually_constructed":null,"ran_individually_by_status":{"ran_honours":1},"end_to_end":{"ran":true,"level":3,"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":"c85e33a81157","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":"9cd82a3f7048523f","source_kind":"harvested","method_name":"Randomized Ensembled Double Q-Learning (REDQ)","realizes_method":"Randomized Ensembled Double Q-Learning (REDQ)","graph_method":"Randomized Ensembled Double Q-Learning (REDQ)","realizes_severed":false,"claim":"The code implements Randomized Ensembled Double Q-Learning (REDQ), a model-free algorithm that uses an ensemble of Q-functions and randomized subset selection for target value estimation to achieve high sample efficiency.","centrality":"contribution","entry":"REDQSACAgent","entry_sha256":"3fdc856200e86955","n_bricks":7,"bricks":[{"entry":"REDQSACAgent","code_sha256":"3fdc856200e86955","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Mlp","code_sha256":"3ec1489c1ccfeec3","role":"model","order":1,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"820da6f0b914ce98","role":"sampler","order":2,"level":1,"status":"ran"},{"entry":"TanhGaussianPolicy","code_sha256":"1172d63a1c99206d","role":"model","order":3,"level":1,"status":"ran"},{"entry":"get_probabilistic_num_min","code_sha256":"dfde273b47c42786","role":"helper","order":4,"level":1,"status":"ran_honours"},{"entry":"soft_update_model1_with_model2","code_sha256":"f95d746979ff7da6","role":"update_rule","order":5,"level":0,"status":"unverified"},{"entry":"weights_init_","code_sha256":"0537c4bc8300d410","role":"helper","order":6,"level":0,"status":"unverified"}],"ran_individually":4,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3,"ran_honours":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":"8d5fc6ae0f85","n_siblings":1,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"af80ea2c732767c4","source_kind":"harvested","method_name":"Randomized Ensembled Double Q-Learning (REDQ)","realizes_method":"Randomized Ensembled Double Q-Learning (REDQ)","graph_method":"Randomized Ensembled Double Q-Learning (REDQ)","realizes_severed":false,"claim":"The paper claims that the REDQ_Agent implements Randomized Ensembled Double Q-Learning (REDQ), a model-free algorithm with high sample efficiency for continuous-action DRL benchmarks.","centrality":"contribution","entry":"REDQ_Agent","entry_sha256":"53367310a72ae0a0","n_bricks":4,"bricks":[{"entry":"REDQ_Agent","code_sha256":"53367310a72ae0a0","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Actor","code_sha256":"89265e3225a6d513","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"8e666530dcfbca00","role":"model","order":2,"level":1,"status":"ran"},{"entry":"hidden_init","code_sha256":"24ee38e114b38bce","role":"helper","order":3,"level":1,"status":"ran_honours"}],"ran_individually":4,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3,"ran_honours":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":"8d5fc6ae0f85","n_siblings":1,"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":"8d5fc6ae0f85","realizes_method":"Randomized Ensembled Double Q-Learning (REDQ)","source_kind":"harvested","batch_at":"2026-09-09T22:44:46+00:00","members":["9cd82a3f7048523f","af80ea2c732767c4"]},{"group":"c85e33a81157","realizes_method":"Randomized Ensembled Double Q-Learning (REDQ)","source_kind":"generated","batch_at":"2026-09-07T20:44:12+00:00","members":["8b0063c84f086407"]}],"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":"2101.05982"},"call":"assembly(arxiv_id=\"2101.05982\")"},"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/2101.05982.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/2101.05982.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/watchernyu/REDQ","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BY571/Randomized-Ensembled-Double-Q-learning-REDQ-","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ustcmike/adaeq_neurips21","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LucasAlegre/sac-plus","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/trackmania-rl/tmrl","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/rl/tree/main/examples/redq/redq.py","reach":null}],"summary":{"ran":4,"unverified":1},"n_samples":5,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"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":{"listed":{"samples":5,"ran":4,"n_ran_checked":4,"n_instrument":0,"repositories":2}},"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"},"official_not_harvested":{"repositories":["watchernyu/REDQ"],"harvested_for_other_papers":[1],"samples_from_other_repositories":5,"other_repositories":2,"samples_unlocated":0},"n_pointer_only_for_licence":3,"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,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing","signature_not_shown":"the graph records a signature for this sample and it is not shown; signature_not_shown_because names why, as the export's field-exclusion reason","signature_not_shown_because":{"signature_is_harness_probe_not_fixture_args":"for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments"}},"n_ran_with_level_date":4,"n_ran_without_level_date":0,"n_ran_signature_not_shown":2,"levels_written_between":{"first":"2026-09-22","last":"2026-09-22","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"89265e3225a6d513","code_sha256_prefix":"89265e3225a6d513","entry":"Actor","repo":"BY571/Randomized-Ensembled-Double-Q-learning-REDQ-","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/BY571/Randomized-Ensembled-Double-Q-learning-REDQ-/blob/HEAD/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"89265e3225a6d513"},"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, BY571/Randomized-Ensembled-Double-Q-learning-REDQ- when it was checked","mcp_get_code":{"code_sha256":"89265e3225a6d513"}},{"code_sha256":"8e666530dcfbca00","code_sha256_prefix":"8e666530dcfbca00","entry":"Critic","repo":"BY571/Randomized-Ensembled-Double-Q-learning-REDQ-","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/BY571/Randomized-Ensembled-Double-Q-learning-REDQ-/blob/HEAD/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, BY571/Randomized-Ensembled-Double-Q-learning-REDQ- when it was checked","mcp_get_code":{"code_sha256":"8e666530dcfbca00"}},{"code_sha256":"53367310a72ae0a0","code_sha256_prefix":"53367310a72ae0a0","entry":"REDQ_Agent","repo":"BY571/Randomized-Ensembled-Double-Q-learning-REDQ-","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/BY571/Randomized-Ensembled-Double-Q-learning-REDQ-/blob/HEAD/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"REDQ_Agent","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","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, BY571/Randomized-Ensembled-Double-Q-learning-REDQ- when it was checked","mcp_get_code":{"code_sha256":"53367310a72ae0a0"}},{"code_sha256":"1172d63a1c99206d","code_sha256_prefix":"1172d63a1c99206d","entry":"TanhGaussianPolicy","repo":"ustcmike/adaeq_neurips21","repo_kind":"listed","path":"redq/algos/redq_sac.py","file_url":"https://github.com/ustcmike/adaeq_neurips21/blob/HEAD/redq/algos/redq_sac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"TanhGaussianPolicy","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"1172d63a1c99206d"},"code_page":"/code/tanhgaussianpolicy","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"1172d63a1c99206d"}},{"code_sha256":"3fdc856200e86955","code_sha256_prefix":"3fdc856200e86955","entry":"REDQSACAgent","repo":"ustcmike/adaeq_neurips21","repo_kind":"listed","path":"redq/algos/redq_sac.py","file_url":"https://github.com/ustcmike/adaeq_neurips21/blob/HEAD/redq/algos/redq_sac.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":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3fdc856200e86955"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"56e308c9eaeafb8904697a4831caf116bd39c2c0635a1b023583056eddea4e02","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}