{"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/minimum-delay-adaptation-in-non-stationary","title":"Minimum-Delay Adaptation in Non-Stationary Reinforcement Learning via Online High-Confidence Change-Point Detection","arxiv_id":"2105.09452","date":"2021-05-20","proceeding":null,"authors":["Lucas N. Alegre","Ana L. C. Bazzan","Bruno C. da Silva"],"abstract":"Non-stationary environments are challenging for reinforcement learning algorithms. If the state transition and/or reward functions change based on latent factors, the agent is effectively tasked with optimizing a behavior that maximizes performance over a possibly infinite random sequence of Markov Decision Processes (MDPs), each of which drawn from some unknown distribution. We call each such MDP a context. Most related works make strong assumptions such as knowledge about the distribution over contexts, the existence of pre-training phases, or a priori knowledge about the number, sequence, or boundaries between contexts. We introduce an algorithm that efficiently learns policies in non-stationary environments. It analyzes a possibly infinite stream of data and computes, in real-time, high-confidence change-point detection statistics that reflect whether novel, specialized policies need to be created and deployed to tackle novel contexts, or whether previously-optimized ones might be reused. We show that (i) this algorithm minimizes the delay until unforeseen changes to a context are detected, thereby allowing for rapid responses; and (ii) it bounds the rate of false alarm, which is important in order to minimize regret. Our method constructs a mixture model composed of a (possibly infinite) ensemble of probabilistic dynamics predictors that model the different modes of the distribution over underlying latent MDPs. We evaluate our algorithm on high-dimensional continuous reinforcement learning problems and show that it outperforms state-of-the-art (model-free and model-based) RL algorithms, as well as state-of-the-art meta-learning methods specially designed to deal with non-stationarity.","url_abs":"https://arxiv.org/abs/2105.09452v1","url_pdf":"https://arxiv.org/pdf/2105.09452v1.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":"minimum-delay-adaptation-in-non-stationary","repo_url":"https://github.com/LucasAlegre/mbcd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"change-point-detection","task_name":"Change Point Detection"},{"task_slug":"meta-learning","task_name":"Meta-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":null,"atlas_url":"https://app.syntology.ai/?focus=2105.09452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.09452"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LucasAlegre/mbcd","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"unverified":9},"by_repo_kind":{"official":{"samples":12,"ran":3,"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":"1bb5583dba32f555","entry":"format_samples_for_training","repo":"LucasAlegre/mbcd","repo_kind":"official","path":"mbcd/models/constructor.py","file_url":"https://github.com/LucasAlegre/mbcd/blob/HEAD/mbcd/models/constructor.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1bb5583dba32f555"}},{"code_sha256_prefix":"4eb5226056a1f70f","entry":"get_required_argument","repo":"LucasAlegre/mbcd","repo_kind":"official","path":"mbcd/models/utils.py","file_url":"https://github.com/LucasAlegre/mbcd/blob/HEAD/mbcd/models/utils.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4eb5226056a1f70f"}},{"code_sha256_prefix":"0cb9b8299fe38738","entry":"ortho_init","repo":"LucasAlegre/mbcd","repo_kind":"official","path":"mbcd/models/fc.py","file_url":"https://github.com/LucasAlegre/mbcd/blob/HEAD/mbcd/models/fc.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0cb9b8299fe38738"}},{"code_sha256_prefix":"fd947865eafc33e9","entry":"alive_bonus","repo":"LucasAlegre/mbcd","repo_kind":"official","path":"mbcd/models/fake_env.py","file_url":"https://github.com/LucasAlegre/mbcd/blob/HEAD/mbcd/models/fake_env.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd947865eafc33e9"}},{"code_sha256_prefix":"6847f28a35bbacb4","entry":"denormalize","repo":"LucasAlegre/mbcd","repo_kind":"official","path":"mbcd/utils/dataset.py","file_url":"https://github.com/LucasAlegre/mbcd/blob/HEAD/mbcd/utils/dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6847f28a35bbacb4"}},{"code_sha256_prefix":"7829b5452293cc7c","entry":"evaluate","repo":"LucasAlegre/mbcd","repo_kind":"official","path":"mbcd/utils/util.py","file_url":"https://github.com/LucasAlegre/mbcd/blob/HEAD/mbcd/utils/util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7829b5452293cc7c"}},{"code_sha256_prefix":"846a50c4e950e840","entry":"kl_mvn","repo":"LucasAlegre/mbcd","repo_kind":"official","path":"mbcd/utils/util.py","file_url":"https://github.com/LucasAlegre/mbcd/blob/HEAD/mbcd/utils/util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"846a50c4e950e840"}},{"code_sha256_prefix":"adae040054a625aa","entry":"linear_schedule","repo":"LucasAlegre/mbcd","repo_kind":"official","path":"mbcd/utils/util.py","file_url":"https://github.com/LucasAlegre/mbcd/blob/HEAD/mbcd/utils/util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"adae040054a625aa"}},{"code_sha256_prefix":"f608d785cedcce04","entry":"normalize","repo":"LucasAlegre/mbcd","repo_kind":"official","path":"mbcd/utils/dataset.py","file_url":"https://github.com/LucasAlegre/mbcd/blob/HEAD/mbcd/utils/dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f608d785cedcce04"}},{"code_sha256_prefix":"dc8918b0020c572d","entry":"termination_fn_hopper","repo":"LucasAlegre/mbcd","repo_kind":"official","path":"mbcd/models/fake_env.py","file_url":"https://github.com/LucasAlegre/mbcd/blob/HEAD/mbcd/models/fake_env.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dc8918b0020c572d"}},{"code_sha256_prefix":"e7212f3e6b7280b5","entry":"termination_fn_hopper_roboschool","repo":"LucasAlegre/mbcd","repo_kind":"official","path":"mbcd/models/fake_env.py","file_url":"https://github.com/LucasAlegre/mbcd/blob/HEAD/mbcd/models/fake_env.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e7212f3e6b7280b5"}},{"code_sha256_prefix":"7f8faab22d304fad","entry":"total_episode_reward_logger","repo":"LucasAlegre/mbcd","repo_kind":"official","path":"mbcd/sac_mbcd.py","file_url":"https://github.com/LucasAlegre/mbcd/blob/HEAD/mbcd/sac_mbcd.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7f8faab22d304fad"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}