{"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/lifelong-reinforcement-learning-with","title":"Lifelong Reinforcement Learning with Modulating Masks","arxiv_id":"2212.11110","date":"2022-12-21","proceeding":null,"authors":["Eseoghene Ben-Iwhiwhu","Saptarshi Nath","Praveen K. Pilly","Soheil Kolouri","Andrea Soltoggio"],"abstract":"Lifelong learning aims to create AI systems that continuously and incrementally learn during a lifetime, similar to biological learning. Attempts so far have met problems, including catastrophic forgetting, interference among tasks, and the inability to exploit previous knowledge. While considerable research has focused on learning multiple supervised classification tasks that involve changes in the input distribution, lifelong reinforcement learning (LRL) must deal with variations in the state and transition distributions, and in the reward functions. Modulating masks with a fixed backbone network, recently developed for classification, are particularly suitable to deal with such a large spectrum of task variations. In this paper, we adapted modulating masks to work with deep LRL, specifically PPO and IMPALA agents. The comparison with LRL baselines in both discrete and continuous RL tasks shows superior performance. We further investigated the use of a linear combination of previously learned masks to exploit previous knowledge when learning new tasks: not only is learning faster, the algorithm solves tasks that we could not otherwise solve from scratch due to extremely sparse rewards. The results suggest that RL with modulating masks is a promising approach to lifelong learning, to the composition of knowledge to learn increasingly complex tasks, and to knowledge reuse for efficient and faster learning.","url_abs":"https://arxiv.org/abs/2212.11110v3","url_pdf":"https://arxiv.org/pdf/2212.11110v3.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":"lifelong-reinforcement-learning-with","repo_url":"https://github.com/dlpbc/mask-lrl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"lifelong-reinforcement-learning-with","repo_url":"https://github.com/soltoggio/ct-graph","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"lifelong-reinforcement-learning-with","repo_url":"https://github.com/DMIU-ShELL/MOSAIC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"lifelong-reinforcement-learning-with","repo_url":"https://github.com/dmiu-shell/deeprl-shell","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"lifelong-learning","task_name":"Lifelong learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"entropy-regularization","method_name":"Entropy Regularization"},{"method_slug":"experience-replay","method_name":"Experience Replay"},{"method_slug":"gradient-clipping","method_name":"Gradient Clipping"},{"method_slug":"impala","method_name":"IMPALA"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"ppo","method_name":"PPO"},{"method_slug":"rmsprop","method_name":"RMSProp"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"v-trace","method_name":"V-trace"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.11110","atlas_url":"https://app.syntology.ai/?focus=2212.11110","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":"2212.11110"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2212.11110\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2212.11110"},"call":"get_concepts_for_paper(arxiv_id=\"2212.11110\")"}],"by_repo":[{"repo":"dlpbc/mask-lrl","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2410.11262"],"harvested_for_calls":[{"arxiv_id":"2410.11262","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.11262"},"call":"get_harvested_code_for_paper(arxiv_id=\"2410.11262\")"}]},{"repo":"soltoggio/ct-graph","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"DMIU-ShELL/MOSAIC","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1707.06347"],"harvested_for_calls":[{"arxiv_id":"1707.06347","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1707.06347"},"call":"get_harvested_code_for_paper(arxiv_id=\"1707.06347\")"}]},{"repo":"dmiu-shell/deeprl-shell","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["1707.06347","2006.14769"],"harvested_for_calls":[{"arxiv_id":"1707.06347","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1707.06347"},"call":"get_harvested_code_for_paper(arxiv_id=\"1707.06347\")"},{"arxiv_id":"2006.14769","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.14769"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.14769\")"}]}],"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"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"284d4cccfa9c441f0020f8fd67548995261ae0b8fce3750cffcdac5b4767953f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}