{"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/selective-experience-replay-for-lifelong","title":"Selective Experience Replay for Lifelong Learning","arxiv_id":"1802.10269","date":"2018-02-28","proceeding":null,"authors":["David Isele","Akansel Cosgun"],"abstract":"Deep reinforcement learning has emerged as a powerful tool for a variety of\nlearning tasks, however deep nets typically exhibit forgetting when learning\nmultiple tasks in sequence. To mitigate forgetting, we propose an experience\nreplay process that augments the standard FIFO buffer and selectively stores\nexperiences in a long-term memory. We explore four strategies for selecting\nwhich experiences will be stored: favoring surprise, favoring reward, matching\nthe global training distribution, and maximizing coverage of the state space.\nWe show that distribution matching successfully prevents catastrophic\nforgetting, and is consistently the best approach on all domains tested. While\ndistribution matching has better and more consistent performance, we identify\none case in which coverage maximization is beneficial - when tasks that receive\nless trained are more important. Overall, our results show that selective\nexperience replay, when suitable selection algorithms are employed, can prevent\ncatastrophic forgetting.","url_abs":"http://arxiv.org/abs/1802.10269v1","url_pdf":"http://arxiv.org/pdf/1802.10269v1.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":"selective-experience-replay-for-lifelong","repo_url":"https://github.com/bossdm/LifelongRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"lifelong-learning","task_name":"Lifelong learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.10269","atlas_url":"https://app.syntology.ai/?focus=1802.10269","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1802.10269"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1802.10269\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1802.10269"},"call":"get_concepts_for_paper(arxiv_id=\"1802.10269\")"}],"by_repo":[{"repo":"bossdm/LifelongRL","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"75c3bdafa9dbf7371d04f136d24d7afa79fd5bb6c129a24e5904a1cf226f21a6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}