{"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/a-study-of-plasticity-loss-in-on-policy-deep","title":"A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning","arxiv_id":"2405.19153","date":"2024-05-29","proceeding":null,"authors":["Arthur Juliani","Jordan T. Ash"],"abstract":"Continual learning with deep neural networks presents challenges distinct from both the fixed-dataset and convex continual learning regimes. One such challenge is plasticity loss, wherein a neural network trained in an online fashion displays a degraded ability to fit new tasks. This problem has been extensively studied in both supervised learning and off-policy reinforcement learning (RL), where a number of remedies have been proposed. Still, plasticity loss has received less attention in the on-policy deep RL setting. Here we perform an extensive set of experiments examining plasticity loss and a variety of mitigation methods in on-policy deep RL. We demonstrate that plasticity loss is pervasive under domain shift in this regime, and that a number of methods developed to resolve it in other settings fail, sometimes even performing worse than applying no intervention at all. In contrast, we find that a class of ``regenerative'' methods are able to consistently mitigate plasticity loss in a variety of contexts, including in gridworld tasks and more challenging environments like Montezuma's Revenge and ProcGen.","url_abs":"https://arxiv.org/abs/2405.19153v2","url_pdf":"https://arxiv.org/pdf/2405.19153v2.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":"a-study-of-plasticity-loss-in-on-policy-deep","repo_url":"https://github.com/awjuliani/deep-rl-plasticity","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"montezumas-revenge","task_name":"Montezuma's Revenge"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.19153","atlas_url":"https://app.syntology.ai/?focus=2405.19153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19153"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/awjuliani/deep-rl-plasticity","reach":{"status":"ok"}}],"summary":{"ran":7,"unverified":4},"by_repo_kind":{"official":{"samples":11,"ran":7,"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":11,"samples":[{"code_sha256_prefix":"cb2beb9c317256e2","entry":"calculate_l2_norm","repo":"awjuliani/deep-rl-plasticity","repo_kind":"official","path":"shared/modules.py","file_url":"https://github.com/awjuliani/deep-rl-plasticity/blob/HEAD/shared/modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cb2beb9c317256e2"}},{"code_sha256_prefix":"da95062042edd8e1","entry":"compute_stats","repo":"awjuliani/deep-rl-plasticity","repo_kind":"official","path":"shared/runner.py","file_url":"https://github.com/awjuliani/deep-rl-plasticity/blob/HEAD/shared/runner.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"da95062042edd8e1"}},{"code_sha256_prefix":"56d3e18414be5388","entry":"permute_image","repo":"awjuliani/deep-rl-plasticity","repo_kind":"official","path":"envs/mdps.py","file_url":"https://github.com/awjuliani/deep-rl-plasticity/blob/HEAD/envs/mdps.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"56d3e18414be5388"}},{"code_sha256_prefix":"11df1d90eebcff7b","entry":"plot_result_rliable","repo":"awjuliani/deep-rl-plasticity","repo_kind":"official","path":"shared/plotting.py","file_url":"https://github.com/awjuliani/deep-rl-plasticity/blob/HEAD/shared/plotting.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"11df1d90eebcff7b"}},{"code_sha256_prefix":"3541cbfdecc9d36f","entry":"r2_score","repo":"awjuliani/deep-rl-plasticity","repo_kind":"official","path":"analyze_helpers.py","file_url":"https://github.com/awjuliani/deep-rl-plasticity/blob/HEAD/analyze_helpers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3541cbfdecc9d36f"}},{"code_sha256_prefix":"ddbd7bdbf2b4393f","entry":"save_param_state","repo":"awjuliani/deep-rl-plasticity","repo_kind":"official","path":"shared/modules.py","file_url":"https://github.com/awjuliani/deep-rl-plasticity/blob/HEAD/shared/modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ddbd7bdbf2b4393f"}},{"code_sha256_prefix":"d68e1e66946f8dc3","entry":"smooth_data","repo":"awjuliani/deep-rl-plasticity","repo_kind":"official","path":"shared/plotting.py","file_url":"https://github.com/awjuliani/deep-rl-plasticity/blob/HEAD/shared/plotting.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d68e1e66946f8dc3"}},{"code_sha256_prefix":"5ac863c022708891","entry":"columnwise_mean_std","repo":"awjuliani/deep-rl-plasticity","repo_kind":"official","path":"analyze_helpers.py","file_url":"https://github.com/awjuliani/deep-rl-plasticity/blob/HEAD/analyze_helpers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5ac863c022708891"}},{"code_sha256_prefix":"06f1efb05beca508","entry":"gen_encoder","repo":"awjuliani/deep-rl-plasticity","repo_kind":"official","path":"shared/modules.py","file_url":"https://github.com/awjuliani/deep-rl-plasticity/blob/HEAD/shared/modules.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"06f1efb05beca508"}},{"code_sha256_prefix":"6be90cf092b46eca","entry":"plot_result","repo":"awjuliani/deep-rl-plasticity","repo_kind":"official","path":"shared/plotting.py","file_url":"https://github.com/awjuliani/deep-rl-plasticity/blob/HEAD/shared/plotting.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6be90cf092b46eca"}},{"code_sha256_prefix":"c791bfb5e5f3a0d7","entry":"process_data","repo":"awjuliani/deep-rl-plasticity","repo_kind":"official","path":"analyze_helpers.py","file_url":"https://github.com/awjuliani/deep-rl-plasticity/blob/HEAD/analyze_helpers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c791bfb5e5f3a0d7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}