{"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/sigmoid-weighted-linear-units-for-neural","title":"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning","arxiv_id":"1702.03118","date":"2017-02-10","proceeding":null,"authors":["Stefan Elfwing","Eiji Uchibe","Kenji Doya"],"abstract":"In recent years, neural networks have enjoyed a renaissance as function\napproximators in reinforcement learning. Two decades after Tesauro's TD-Gammon\nachieved near top-level human performance in backgammon, the deep reinforcement\nlearning algorithm DQN achieved human-level performance in many Atari 2600\ngames. The purpose of this study is twofold. First, we propose two activation\nfunctions for neural network function approximation in reinforcement learning:\nthe sigmoid-weighted linear unit (SiLU) and its derivative function (dSiLU).\nThe activation of the SiLU is computed by the sigmoid function multiplied by\nits input. Second, we suggest that the more traditional approach of using\non-policy learning with eligibility traces, instead of experience replay, and\nsoftmax action selection with simple annealing can be competitive with DQN,\nwithout the need for a separate target network. We validate our proposed\napproach by, first, achieving new state-of-the-art results in both stochastic\nSZ-Tetris and Tetris with a small 10$\\times$10 board, using TD($\\lambda$)\nlearning and shallow dSiLU network agents, and, then, by outperforming DQN in\nthe Atari 2600 domain by using a deep Sarsa($\\lambda$) agent with SiLU and\ndSiLU hidden units.","url_abs":"http://arxiv.org/abs/1702.03118v3","url_pdf":"http://arxiv.org/pdf/1702.03118v3.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":[],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement 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":"dqn","method_name":"DQN"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"q-learning","method_name":"Q-Learning"},{"method_slug":"silu","method_name":"SiLU"}],"datasets_introduced":[],"methods_introduced":[{"slug":"silu","name":"SiLU","full_name":"Sigmoid Linear Unit"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1702.03118","atlas_url":"https://app.syntology.ai/?focus=1702.03118","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":"1702.03118"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1702.03118\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1702.03118"},"call":"get_concepts_for_paper(arxiv_id=\"1702.03118\")"}],"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"44eef9c2f389a6620d5be3503b0e93c4434b0a210b1fd5346f8f529b74c6330c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}