{"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/continual-reinforcement-learning-with-multi","title":"Continual Reinforcement Learning with Multi-Timescale Replay","arxiv_id":"2004.07530","date":"2020-04-16","proceeding":null,"authors":["Christos Kaplanis","Claudia Clopath","Murray Shanahan"],"abstract":"In this paper, we propose a multi-timescale replay (MTR) buffer for improving continual learning in RL agents faced with environments that are changing continuously over time at timescales that are unknown to the agent. The basic MTR buffer comprises a cascade of sub-buffers that accumulate experiences at different timescales, enabling the agent to improve the trade-off between adaptation to new data and retention of old knowledge. We also combine the MTR framework with invariant risk minimization, with the idea of encouraging the agent to learn a policy that is robust across the various environments it encounters over time. The MTR methods are evaluated in three different continual learning settings on two continuous control tasks and, in many cases, show improvement over the baselines.","url_abs":"https://arxiv.org/abs/2004.07530v1","url_pdf":"https://arxiv.org/pdf/2004.07530v1.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":"continual-reinforcement-learning-with-multi","repo_url":"https://github.com/ChristosKap/multi_timescale_replay","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"continuous-control","task_name":"Continuous Control"},{"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2004.07530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.07530"}},"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/ChristosKap/multi_timescale_replay","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"ran":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":0,"samples":[{"code_sha256_prefix":"564b2893eba1695b","entry":"fixed_params_half_cheetah","repo":"ChristosKap/multi_timescale_replay","repo_kind":"official","path":"env_schedules.py","file_url":"https://github.com/ChristosKap/multi_timescale_replay/blob/HEAD/env_schedules.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":"564b2893eba1695b"}},{"code_sha256_prefix":"30442e0c664c94cb","entry":"gaussian_entropy","repo":"ChristosKap/multi_timescale_replay","repo_kind":"official","path":"policies.py","file_url":"https://github.com/ChristosKap/multi_timescale_replay/blob/HEAD/policies.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":"30442e0c664c94cb"}},{"code_sha256_prefix":"d83bd3d48376102b","entry":"gaussian_likelihood","repo":"ChristosKap/multi_timescale_replay","repo_kind":"official","path":"policies.py","file_url":"https://github.com/ChristosKap/multi_timescale_replay/blob/HEAD/policies.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":"d83bd3d48376102b"}},{"code_sha256_prefix":"98bc8c210ba8fb2a","entry":"get_eval_schedule_fn","repo":"ChristosKap/multi_timescale_replay","repo_kind":"official","path":"env_schedules.py","file_url":"https://github.com/ChristosKap/multi_timescale_replay/blob/HEAD/env_schedules.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":"98bc8c210ba8fb2a"}},{"code_sha256_prefix":"10592ec21afcbd16","entry":"get_nb_env_params","repo":"ChristosKap/multi_timescale_replay","repo_kind":"official","path":"env_schedules.py","file_url":"https://github.com/ChristosKap/multi_timescale_replay/blob/HEAD/env_schedules.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":"10592ec21afcbd16"}},{"code_sha256_prefix":"5a90b968f3e71b81","entry":"get_replay_buffer","repo":"ChristosKap/multi_timescale_replay","repo_kind":"official","path":"replay_buffers.py","file_url":"https://github.com/ChristosKap/multi_timescale_replay/blob/HEAD/replay_buffers.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":"5a90b968f3e71b81"}},{"code_sha256_prefix":"92cc14336109c580","entry":"proportional","repo":"ChristosKap/multi_timescale_replay","repo_kind":"official","path":"replay_buffers.py","file_url":"https://github.com/ChristosKap/multi_timescale_replay/blob/HEAD/replay_buffers.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":"92cc14336109c580"}},{"code_sha256_prefix":"b7dcc9f1fe62457e","entry":"squashed_gaussian_likelihood","repo":"ChristosKap/multi_timescale_replay","repo_kind":"official","path":"policies.py","file_url":"https://github.com/ChristosKap/multi_timescale_replay/blob/HEAD/policies.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":"b7dcc9f1fe62457e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}