{"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/offline-reinforcement-learning-from-datasets","title":"Offline Reinforcement Learning from Datasets with Structured Non-Stationarity","arxiv_id":"2405.14114","date":"2024-05-23","proceeding":null,"authors":["Johannes Ackermann","Takayuki Osa","Masashi Sugiyama"],"abstract":"Current Reinforcement Learning (RL) is often limited by the large amount of data needed to learn a successful policy. Offline RL aims to solve this issue by using transitions collected by a different behavior policy. We address a novel Offline RL problem setting in which, while collecting the dataset, the transition and reward functions gradually change between episodes but stay constant within each episode. We propose a method based on Contrastive Predictive Coding that identifies this non-stationarity in the offline dataset, accounts for it when training a policy, and predicts it during evaluation. We analyze our proposed method and show that it performs well in simple continuous control tasks and challenging, high-dimensional locomotion tasks. We show that our method often achieves the oracle performance and performs better than baselines.","url_abs":"https://arxiv.org/abs/2405.14114v2","url_pdf":"https://arxiv.org/pdf/2405.14114v2.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":"offline-reinforcement-learning-from-datasets","repo_url":"https://github.com/johannesack/offlinerlstructurednonstationarity","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"offline-rl","task_name":"Offline RL"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"continuous-control","task_name":"continuous-control"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"contrastive-predictive-coding","method_name":"Contrastive Predictive Coding"},{"method_slug":"infonce","method_name":"InfoNCE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.14114","atlas_url":"https://app.syntology.ai/?focus=2405.14114","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14114"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2405.14114"},"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_harvested_code_for_paper","arguments":{"arxiv_id":"2405.14114"},"call":"get_harvested_code_for_paper(arxiv_id=\"2405.14114\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2405.14114"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2405.14114\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2405.14114"},"call":"get_concepts_for_paper(arxiv_id=\"2405.14114\")"}],"by_repo":[{"repo":"johannesack/offlinerlstructurednonstationarity","kind":"official","samples":12,"ran":10,"instrument":2,"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","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/2405.14114.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/2405.14114.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/johannesack/offlinerlstructurednonstationarity","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"ran":8,"unverified":2},"n_samples":12,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"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":12,"ran":10,"n_ran_checked":8,"n_instrument":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,"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"},"n_ran_with_level_date":10,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","last":"2026-09-24","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":"56aec01f040cabad","code_sha256_prefix":"56aec01f040cabad","entry":"default_mlp_init","repo":"johannesack/offlinerlstructurednonstationarity","repo_kind":"official","path":"representation_models/cpc_model.py","file_url":"https://github.com/johannesack/offlinerlstructurednonstationarity/blob/HEAD/representation_models/cpc_model.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"scale:float/0/float","fixture_out_type":"function","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"56aec01f040cabad"}},{"code_sha256":"63edece0ba36d0d6","code_sha256_prefix":"63edece0ba36d0d6","entry":"draw_circle","repo":"johannesack/offlinerlstructurednonstationarity","repo_kind":"official","path":"custom_env/hip_environment.py","file_url":"https://github.com/johannesack/offlinerlstructurednonstationarity/blob/HEAD/custom_env/hip_environment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"edit_array:ArrayImpl/3/int, pos:ArrayImpl/1/float, radius:float/0/float, color:list/1/int, space_size:int/0/int, size:int/0/int","fixture_out_type":"ArrayImpl","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"63edece0ba36d0d6"}},{"code_sha256":"de59f09f6434b29d","code_sha256_prefix":"de59f09f6434b29d","entry":"get_actor_loss","repo":"johannesack/offlinerlstructurednonstationarity","repo_kind":"official","path":"RLMethods/TD3BCTrainer.py","file_url":"https://github.com/johannesack/offlinerlstructurednonstationarity/blob/HEAD/RLMethods/TD3BCTrainer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"actor_params:FrozenDict/0/?, critic_params:FrozenDict/0/?, actor_apply_fn:callable/0/?, critic_apply_fn:callable/0/?, obs:ArrayImpl/2/float, action:ArrayImpl/2/float, td3_alpha:NoneType/0/?","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"de59f09f6434b29d"}},{"code_sha256":"fdce303f39ae0a89","code_sha256_prefix":"fdce303f39ae0a89","entry":"get_actor_loss","repo":"johannesack/offlinerlstructurednonstationarity","repo_kind":"official","path":"RLMethods/TD3Trainer.py","file_url":"https://github.com/johannesack/offlinerlstructurednonstationarity/blob/HEAD/RLMethods/TD3Trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"actor_params:FrozenDict/0/?, critic_params:FrozenDict/0/?, actor_apply_fn:callable/0/?, critic_apply_fn:callable/0/?, obs:ArrayImpl/2/float, action:ArrayImpl/2/float","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"fdce303f39ae0a89"}},{"code_sha256":"9c036454791018b3","code_sha256_prefix":"9c036454791018b3","entry":"get_critic_loss","repo":"johannesack/offlinerlstructurednonstationarity","repo_kind":"official","path":"RLMethods/TD3Trainer.py","file_url":"https://github.com/johannesack/offlinerlstructurednonstationarity/blob/HEAD/RLMethods/TD3Trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"critic_params:FrozenDict/0/?, critic_target_params:FrozenDict/0/?, actor_target_params:FrozenDict/0/?, critic_apply_fn:callable/0/?, actor_apply_fn:callable/0/?, obs:ArrayImpl/2/float, action:ArrayImpl/2/float, reward:ArrayImpl/1/float, done:ArrayImpl/1/float, next_obs:ArrayImpl/2/float, decay:float/0/float, policy_noise_std:float/0/float, policy_noise_clip:float/0/float, max_action:float/0/float, rng_key:ArrayImpl/1/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9c036454791018b3"}},{"code_sha256":"9a00239e9a2e6660","code_sha256_prefix":"9a00239e9a2e6660","entry":"get_linear_probeacc_realtrain_faketest","repo":"johannesack/offlinerlstructurednonstationarity","repo_kind":"official","path":"representation_models/latent_predictor_model.py","file_url":"https://github.com/johannesack/offlinerlstructurednonstationarity/blob/HEAD/representation_models/latent_predictor_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"train_latents:ArrayImpl/3/float, test_latents:ArrayImpl/2/float, train_hips:ndarray/2/int, test_hips:ndarray/1/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9a00239e9a2e6660"}},{"code_sha256":"b9e2cfcaab3117fa","code_sha256_prefix":"b9e2cfcaab3117fa","entry":"get_mse_loss","repo":"johannesack/offlinerlstructurednonstationarity","repo_kind":"official","path":"representation_models/latent_predictor_model.py","file_url":"https://github.com/johannesack/offlinerlstructurednonstationarity/blob/HEAD/representation_models/latent_predictor_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"params:dict/0/?, apply_fn:callable/0/?, context_latents:ArrayImpl/2/float, next_latent_target:ArrayImpl/2/float, rng:ArrayImpl/1/int","fixture_out_type":"ArrayImpl","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b9e2cfcaab3117fa"}},{"code_sha256":"0e1815d7327a86a7","code_sha256_prefix":"0e1815d7327a86a7","entry":"orthogonal_init","repo":"johannesack/offlinerlstructurednonstationarity","repo_kind":"official","path":"RLMethods/rl_models.py","file_url":"https://github.com/johannesack/offlinerlstructurednonstationarity/blob/HEAD/RLMethods/rl_models.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"scale:float/0/float","fixture_out_type":"function","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/orthogonal-init","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0e1815d7327a86a7"}},{"code_sha256":"9e7e7578eb33e5fc","code_sha256_prefix":"9e7e7578eb33e5fc","entry":"sample_batch","repo":"johannesack/offlinerlstructurednonstationarity","repo_kind":"official","path":"RLMethods/TD3BCTrainer.py","file_url":"https://github.com/johannesack/offlinerlstructurednonstationarity/blob/HEAD/RLMethods/TD3BCTrainer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"buffer:dict/0/?, num_existing_samples:int/0/int, config:Config/0/?, rng:ArrayImpl/1/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/sample-batch","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9e7e7578eb33e5fc"}},{"code_sha256":"9dcf8cb33934578d","code_sha256_prefix":"9dcf8cb33934578d","entry":"sample_batch","repo":"johannesack/offlinerlstructurednonstationarity","repo_kind":"official","path":"RLMethods/TD3Trainer.py","file_url":"https://github.com/johannesack/offlinerlstructurednonstationarity/blob/HEAD/RLMethods/TD3Trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"buffer:dict/0/?, num_existing_samples:int/0/int, batch_size:int/0/int, num_train_envs:int/0/int, rng:ArrayImpl/1/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/sample-batch","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9dcf8cb33934578d"}},{"code_sha256":"716cf1c3bc60674c","code_sha256_prefix":"716cf1c3bc60674c","entry":"get_ant_xml","repo":"johannesack/offlinerlstructurednonstationarity","repo_kind":"official","path":"custom_env/leglen_ant.py","file_url":"https://github.com/johannesack/offlinerlstructurednonstationarity/blob/HEAD/custom_env/leglen_ant.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":"716cf1c3bc60674c"}},{"code_sha256":"edb5ab405906d972","code_sha256_prefix":"edb5ab405906d972","entry":"sample_batch_and_update","repo":"johannesack/offlinerlstructurednonstationarity","repo_kind":"official","path":"representation_models/latent_predictor_model.py","file_url":"https://github.com/johannesack/offlinerlstructurednonstationarity/blob/HEAD/representation_models/latent_predictor_model.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":"edb5ab405906d972"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"0d8b1451c919a52ead12042e417f1cfab04cd0b9570aa7dc0a0ca93e215def15","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}