{"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/mastering-continual-reinforcement-learning","title":"Mastering Continual Reinforcement Learning through Fine-Grained Sparse Network Allocation and Dormant Neuron Exploration","arxiv_id":"2503.05246","date":"2025-03-07","proceeding":null,"authors":["Chengqi Zheng","Haiyan Yin","Jianda Chen","Terence Ng","Yew-Soon Ong","Ivor Tsang"],"abstract":"Continual Reinforcement Learning (CRL) is essential for developing agents that can learn, adapt, and accumulate knowledge over time. However, a fundamental challenge persists as agents must strike a delicate balance between plasticity, which enables rapid skill acquisition, and stability, which ensures long-term knowledge retention while preventing catastrophic forgetting. In this paper, we introduce SSDE, a novel structure-based approach that enhances plasticity through a fine-grained allocation strategy with Structured Sparsity and Dormant-guided Exploration. SSDE decomposes the parameter space into forward-transfer (frozen) parameters and task-specific (trainable) parameters. Crucially, these parameters are allocated by an efficient co-allocation scheme under sparse coding, ensuring sufficient trainable capacity for new tasks while promoting efficient forward transfer through frozen parameters. However, structure-based methods often suffer from rigidity due to the accumulation of non-trainable parameters, limiting exploration and adaptability. To address this, we further introduce a sensitivity-guided neuron reactivation mechanism that systematically identifies and resets dormant neurons, which exhibit minimal influence in the sparse policy network during inference. This approach effectively enhance exploration while preserving structural efficiency. Extensive experiments on the CW10-v1 Continual World benchmark demonstrate that SSDE achieves state-of-the-art performance, reaching a success rate of 95%, surpassing prior methods significantly in both plasticity and stability trade-offs (code is available at: https://github.com/chengqiArchy/SSDE).","url_abs":"https://arxiv.org/abs/2503.05246v2","url_pdf":"https://arxiv.org/pdf/2503.05246v2.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":"mastering-continual-reinforcement-learning","repo_url":"https://github.com/chengqiarchy/ssde","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.05246","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.05246"}},"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/chengqiarchy/ssde","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"929fbcc94c924084","entry":"calculate_layer_neuron","repo":"chengqiarchy/ssde","repo_kind":"official","path":"train_ssde.py","file_url":"https://github.com/chengqiarchy/ssde/blob/HEAD/train_ssde.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"929fbcc94c924084"}},{"code_sha256_prefix":"9082dbf908519ba4","entry":"get_each_layer_neuron_difference","repo":"chengqiarchy/ssde","repo_kind":"official","path":"train_ssde.py","file_url":"https://github.com/chengqiarchy/ssde/blob/HEAD/train_ssde.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9082dbf908519ba4"}},{"code_sha256_prefix":"abcc3f56fabb7669","entry":"get_each_layer_reset_indices","repo":"chengqiarchy/ssde","repo_kind":"official","path":"train_ssde.py","file_url":"https://github.com/chengqiarchy/ssde/blob/HEAD/train_ssde.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"abcc3f56fabb7669"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}