{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T00:56:15Z","timestamp":1773449775095,"version":"3.50.1"},"reference-count":73,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,10,27]],"date-time":"2027-10-27T00:00:00Z","timestamp":1824595200000},"content-version":"am","delay-in-days":605,"URL":"http:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","award":["JPMJPR22C5"],"award-info":[{"award-number":["JPMJPR22C5"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","award":["JPMJMS2021"],"award-info":[{"award-number":["JPMJMS2021"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","award":["JPJ012207"],"award-info":[{"award-number":["JPJ012207"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004721","name":"University of Tokyo","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004721","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP22K17969"],"award-info":[{"award-number":["JP22K17969"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP22KK0159"],"award-info":[{"award-number":["JP22KK0159"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JPNP14004"],"award-info":[{"award-number":["JPNP14004"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP25K00148"],"award-info":[{"award-number":["JP25K00148"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001863","name":"New Energy and Industrial Technology Development Organization","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001863","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000026","name":"Institute of Aging","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000026","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1016\/j.neunet.2025.108202","type":"journal-article","created":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T16:00:27Z","timestamp":1760544027000},"page":"108202","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["Chaos-based reinforcement learning with TD3"],"prefix":"10.1016","volume":"195","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1908-2451","authenticated-orcid":false,"given":"Toshitaka","family":"Matsuki","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0274-9491","authenticated-orcid":false,"given":"Yusuke","family":"Sakemi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4602-9816","authenticated-orcid":false,"given":"Kazuyuki","family":"Aihara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.neunet.2025.108202_bib0001","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/S0893-6080(96)00061-5","article-title":"Associative dynamics in a chaotic neural network","volume":"10","author":"Adachi","year":"1997","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.108202_bib0002","doi-asserted-by":"crossref","first-page":"62","DOI":"10.70470\/EDRAAK\/2025\/009","article-title":"Enhancing economic growth time series for UAE forecasting with deep learning: a seq2seq and attention-driven LSTM approach","volume":"2025","author":"Adamopoulos","year":"2025","journal-title":"EDRAAK"},{"issue":"7","key":"10.1016\/j.neunet.2025.108202_bib0003","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1016\/0375-9601(86)90578-5","article-title":"Structures of attractors in periodically forced neural oscillators","volume":"116","author":"Aihara","year":"1986","journal-title":"Physics Letters A"},{"issue":"6\u20137","key":"10.1016\/j.neunet.2025.108202_bib0004","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1016\/0375-9601(90)90136-C","article-title":"Chaotic neural networks","volume":"144","author":"Aihara","year":"1990","journal-title":"Physics Letters A"},{"key":"10.1016\/j.neunet.2025.108202_bib0005","series-title":"International conference on machine learning","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"Amodei","year":"2016"},{"issue":"1864","key":"10.1016\/j.neunet.2025.108202_bib0006","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1098\/rsta.2007.2092","article-title":"The criticality hypothesis: How local cortical networks might optimize information processing","volume":"366","author":"Beggs","year":"2007","journal-title":"Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences"},{"issue":"35","key":"10.1016\/j.neunet.2025.108202_bib0007","doi-asserted-by":"crossref","first-page":"11167","DOI":"10.1523\/JNEUROSCI.23-35-11167.2003","article-title":"Neuronal avalanches in neocortical circuits","volume":"23","author":"Beggs","year":"2003","journal-title":"Journal of Neuroscience"},{"issue":"7","key":"10.1016\/j.neunet.2025.108202_bib0008","doi-asserted-by":"crossref","first-page":"1413","DOI":"10.1162\/089976604323057443","article-title":"Real-time computation at the edge of chaos in recurrent neural networks","volume":"16","author":"Bertschinger","year":"2004","journal-title":"Neural Computation"},{"issue":"3","key":"10.1016\/j.neunet.2025.108202_bib0009","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1007\/s12064-011-0146-8","article-title":"Information processing in echo state networks at the edge of chaos","volume":"131","author":"Boedecker","year":"2012","journal-title":"Theory in Biosciences"},{"issue":"5711","key":"10.1016\/j.neunet.2025.108202_bib0010","doi-asserted-by":"crossref","first-page":"896","DOI":"10.1126\/science.1103736","article-title":"Optical imaging of neuronal populations during decision-making","volume":"307","author":"Briggman","year":"2005","journal-title":"Science"},{"key":"10.1016\/j.neunet.2025.108202_bib0011","unstructured":"Brockman, G., Cheung, V., Pettersson, L., Schneider, J., Schulman, J., Tang, J., & Zaremba, W. (2016). OpenAI Gym. https:\/\/arxiv.org\/abs\/1606.01540."},{"key":"10.1016\/j.neunet.2025.108202_bib0012","unstructured":"Brooks, T., Peebles, B., Homes, C., DePue, W., Guo, Y., Jing, L., Schnurr, D., Taylor, J., Luhman, T., Luhman, E., Ng, C. W. Y., Wang, R., & Ramesh, A. (2024). Video generation models as world simulators. https:\/\/openai.com\/research\/video-generation-models-as-world-simulators."},{"key":"10.1016\/j.neunet.2025.108202_bib0013","series-title":"Ecai 2020","first-page":"1047","article-title":"Model-free non-stationarity detection and adaptation in reinforcement learning","author":"Canonaco","year":"2020"},{"issue":"8","key":"10.1016\/j.neunet.2025.108202_bib0014","doi-asserted-by":"crossref","first-page":"2400","DOI":"10.1007\/s10489-020-01679-3","article-title":"Reinforcement learning with convolutional reservoir computing","volume":"50","author":"Chang","year":"2020","journal-title":"Applied Intelligence"},{"issue":"3","key":"10.1016\/j.neunet.2025.108202_bib0015","doi-asserted-by":"crossref","first-page":"929","DOI":"10.1109\/TNNLS.2020.3029711","article-title":"Deep echo state Q-network (DEQN) and its application in dynamic spectrum sharing for 5G and beyond","volume":"33","author":"Chang","year":"2020","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"6","key":"10.1016\/j.neunet.2025.108202_bib0016","doi-asserted-by":"crossref","first-page":"915","DOI":"10.1016\/0893-6080(95)00033-V","article-title":"Chaotic simulated annealing by a neural network model with transient chaos","volume":"8","author":"Chen","year":"1995","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.108202_bib0017","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv: 1406.1078.","DOI":"10.3115\/v1\/D14-1179"},{"key":"10.1016\/j.neunet.2025.108202_bib0018","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1016\/j.pneurobio.2017.07.002","article-title":"Criticality in the brain: a synthesis of neurobiology, models and cognition","volume":"158","author":"Cocchi","year":"2017","journal-title":"Progress in Neurobiology"},{"key":"10.1016\/j.neunet.2025.108202_bib0019","unstructured":"Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv: 1810.04805."},{"key":"10.1016\/j.neunet.2025.108202_bib0020","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S. et al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv: 2010.11929."},{"issue":"3","key":"10.1016\/j.neunet.2025.108202_bib0021","doi-asserted-by":"crossref","first-page":"1160","DOI":"10.1152\/jn.90592.2008","article-title":"Behavioral states, network states, and sensory response variability","volume":"100","author":"Fontanini","year":"2008","journal-title":"Journal of Neurophysiology"},{"issue":"1","key":"10.1016\/j.neunet.2025.108202_bib0022","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/j.neuron.2007.08.023","article-title":"Intrinsic fluctuations within cortical systems account for intertrial variability in human behavior","volume":"56","author":"Fox","year":"2007","journal-title":"Neuron"},{"key":"10.1016\/j.neunet.2025.108202_bib0023","unstructured":"Franceschelli, G., & Musolesi, M. (2023). On the creativity of large language models. arXiv preprint arXiv: 2304.00008."},{"issue":"2","key":"10.1016\/j.neunet.2025.108202_bib0024","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1038\/scientificamerican0291-78","article-title":"The physiology of perception","volume":"264","author":"Freeman","year":"1991","journal-title":"Scientific American"},{"key":"10.1016\/j.neunet.2025.108202_bib0025","series-title":"International conference on machine learning","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018"},{"issue":"3","key":"10.1016\/j.neunet.2025.108202_bib0026","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1007\/s12559-017-9461-9","article-title":"Echo state property of deep reservoir computing networks","volume":"9","author":"Gallicchio","year":"2017","journal-title":"Cognitive Computation"},{"key":"10.1016\/j.neunet.2025.108202_bib0027","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1016\/j.neucom.2016.12.089","article-title":"Deep reservoir computing: A critical experimental analysis","volume":"268","author":"Gallicchio","year":"2017","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2025.108202_bib0028","series-title":"Neural information processing","first-page":"40","article-title":"Emergence of higher exploration in reinforcement learning using a chaotic neural network","author":"Goto","year":"2016"},{"key":"10.1016\/j.neunet.2025.108202_bib0029","series-title":"Neural information processing","first-page":"759","article-title":"Influence of the chaotic property on reinforcement learning using a chaotic neural network","author":"Goto","year":"2017"},{"key":"10.1016\/j.neunet.2025.108202_bib0030","series-title":"International conference on machine learning","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"Graves","year":"2014"},{"issue":"3","key":"10.1016\/j.neunet.2025.108202_bib0031","doi-asserted-by":"crossref","DOI":"10.1016\/j.yjoc.2023.100065","article-title":"The originality of machines: AI takes the torrance test","volume":"33","author":"Guzik","year":"2023","journal-title":"Journal of Creativity"},{"issue":"2","key":"10.1016\/j.neunet.2025.108202_bib0032","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.neuron.2017.06.011","article-title":"Neuroscience-inspired artificial intelligence","volume":"95","author":"Hassabis","year":"2017","journal-title":"Neuron"},{"key":"10.1016\/j.neunet.2025.108202_bib0033","series-title":"Aaai fall symposia","first-page":"141","article-title":"Deep recurrent Q-learning for partially observable MDPs","volume":"vol. 45","author":"Hausknecht","year":"2015"},{"key":"10.1016\/j.neunet.2025.108202_bib0034","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neunet.2025.108202_bib0035","series-title":"Proceedings of the AAAI conference on artificial intelligence","article-title":"Rainbow: Combining improvements in deep reinforcement learning","volume":"vol. 32","author":"Hessel","year":"2018"},{"issue":"3","key":"10.1016\/j.neunet.2025.108202_bib0036","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1093\/cercor\/bhs348","article-title":"Emergence of complex computational structures from chaotic neural networks through reward-modulated hebbian learning","volume":"24","author":"Hoerzer","year":"2012","journal-title":"Cerebral Cortex"},{"key":"10.1016\/j.neunet.2025.108202_bib0037","unstructured":"Jaeger, H. (2001). The \u201cecho state\u201d approach to analysing and training recurrent neural networks-with an erratum note. Bonn, Germany: German National Research Center for Information Technology GMD Technical Report, 148(34), 13."},{"issue":"8","key":"10.1016\/j.neunet.2025.108202_bib0038","doi-asserted-by":"crossref","first-page":"1430","DOI":"10.1162\/neco_a_01596","article-title":"Maximal memory capacity near the edge of chaos in balanced cortical EI networks","volume":"35","author":"Kanamaru","year":"2023","journal-title":"Neural Computation"},{"issue":"3","key":"10.1016\/j.neunet.2025.108202_bib0039","doi-asserted-by":"crossref","first-page":"926","DOI":"10.1063\/1.1607783","article-title":"Chaotic itinerancy","volume":"13","author":"Kaneko","year":"2003","journal-title":"Chaos: An Interdisciplinary Journal of Nonlinear Science"},{"key":"10.1016\/j.neunet.2025.108202_bib0040","series-title":"Advances in neural information processing systems","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012"},{"key":"10.1016\/j.neunet.2025.108202_bib0041","unstructured":"Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., & Wierstra, D. (2015). Continuous control with deep reinforcement learning. arXiv preprint arXiv: 1509.02971."},{"key":"10.1016\/j.neunet.2025.108202_bib0042","series-title":"Neural networks: Tricks of the trade: Second edition","first-page":"659","article-title":"A practical guide to applying echo state networks","author":"Luko\u0161evi\u010dius","year":"2012"},{"key":"10.1016\/j.neunet.2025.108202_bib0043","unstructured":"Ma, Q., Shen, L., & Cottrell, G. W. (2017). Deep-ESN: A multiple projection-encoding hierarchical reservoir computing framework. arXiv preprint arXiv: 1711.05255."},{"issue":"11","key":"10.1016\/j.neunet.2025.108202_bib0044","doi-asserted-by":"crossref","first-page":"2531","DOI":"10.1162\/089976602760407955","article-title":"Real-time computing without stable states: a new framework for neural computation based on perturbations","volume":"14","author":"Maass","year":"2002","journal-title":"Neural Computation"},{"key":"10.1016\/j.neunet.2025.108202_bib0045","unstructured":"Matsuki, T. (2022). Deep Q-network using reservoir computing with multi-layered readout. arXiv preprint arXiv: 2203.01465."},{"key":"10.1016\/j.neunet.2025.108202_bib0046","series-title":"2020 International joint conference on neural networks (IJCNN)","first-page":"1","article-title":"Q-learning with exploration driven by internal dynamics in chaotic neural network","author":"Matsuki","year":"2020"},{"key":"10.1016\/j.neunet.2025.108202_bib0047","series-title":"International conference on neural information processing","first-page":"376","article-title":"Reward-based learning of a memory-required task based on the internal dynamics of a chaotic neural network","author":"Matsuki","year":"2016"},{"key":"10.1016\/j.neunet.2025.108202_bib0048","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.neunet.2020.08.002","article-title":"Adaptive balancing of exploration and exploitation around the edge of chaos in internal-chaos-based learning","volume":"132","author":"Matsuki","year":"2020","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.108202_bib0049","unstructured":"McCarthy, J., Minsky, M. L., Rochester, N., & Shannon, C. E. (1955). A proposal for the dartmouth summer research project on artificial intelligence."},{"key":"10.1016\/j.neunet.2025.108202_bib0050","series-title":"2021 IEEE\/RSJ international conference on intelligent robots and systems (IROS)","first-page":"5619","article-title":"Memory-based deep reinforcement learning for pomdps","author":"Meng","year":"2021"},{"key":"10.1016\/j.neunet.2025.108202_bib0051","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., & Riedmiller, M. (2013). Playing atari with deep reinforcement learning. arXiv preprint arXiv: 1312.5602."},{"key":"10.1016\/j.neunet.2025.108202_bib0052","unstructured":"Ni, T., Eysenbach, B., & Salakhutdinov, R. (2021). Recurrent model-free RL can be a strong baseline for many pomdps. arXiv preprint arXiv: 2110.05038."},{"issue":"5","key":"10.1016\/j.neunet.2025.108202_bib0053","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1000072","article-title":"Transient cognitive dynamics, metastability, and decision making","volume":"4","author":"Rabinovich","year":"2008","journal-title":"PLoS Computational Biology"},{"key":"10.1016\/j.neunet.2025.108202_bib0054","series-title":"International conference on machine learning","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023"},{"issue":"1","key":"10.1016\/j.neunet.2025.108202_bib0055","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-020-78725-0","article-title":"Model-size reduction for reservoir computing by concatenating internal states through time","volume":"10","author":"Sakemi","year":"2020","journal-title":"Scientific Reports"},{"issue":"1","key":"10.1016\/j.neunet.2025.108202_bib0056","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1038\/s42005-023-01500-w","article-title":"Learning reservoir dynamics with temporal self-modulation","volume":"7","author":"Sakemi","year":"2024","journal-title":"Communications Physics"},{"key":"10.1016\/j.neunet.2025.108202_bib0057","series-title":"Robot intelligence technology and applications","first-page":"76","article-title":"Chaos-based reinforcement learning when introducing refractoriness in each neuron","author":"Sato","year":"2019"},{"key":"10.1016\/j.neunet.2025.108202_bib0058","doi-asserted-by":"crossref","DOI":"10.3389\/fnetp.2021.755685","article-title":"Criticality in the healthy brain","volume":"1","author":"Shi","year":"2022","journal-title":"Frontiers in Network Physiology"},{"key":"10.1016\/j.neunet.2025.108202_bib0059","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1016\/j.neunet.2021.06.015","article-title":"Sensitivity - local index to control chaoticity or gradient globally -","volume":"143","author":"Shibata","year":"2021","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.108202_bib0060","series-title":"2015 international joint conference on neural networks (IJCNN)","first-page":"1","article-title":"Reinforcement learning with internal-dynamics-based exploration using a chaotic neural network","author":"Shibata","year":"2015"},{"issue":"6419","key":"10.1016\/j.neunet.2025.108202_bib0061","doi-asserted-by":"crossref","first-page":"1140","DOI":"10.1126\/science.aar6404","article-title":"A general reinforcement learning algorithm that masters chess, shogi, and go through self-play","volume":"362","author":"Silver","year":"2018","journal-title":"Science"},{"key":"10.1016\/j.neunet.2025.108202_bib0062","series-title":"International conference on machine learning","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"Silver","year":"2014"},{"issue":"7676","key":"10.1016\/j.neunet.2025.108202_bib0063","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"Silver","year":"2017","journal-title":"Nature"},{"issue":"2","key":"10.1016\/j.neunet.2025.108202_bib0064","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1017\/S0140525X00047336","article-title":"How brains make chaos in order to make sense of the world","volume":"10","author":"Skarda","year":"1987","journal-title":"Behavioral and Brain Sciences"},{"key":"10.1016\/j.neunet.2025.108202_bib0065","series-title":"Conference on lifelong learning agents","first-page":"441","article-title":"Reactive exploration to cope with non-stationarity in lifelong reinforcement learning","author":"Steinparz","year":"2022"},{"key":"10.1016\/j.neunet.2025.108202_bib0066","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume":"27","author":"Sutskever","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108202_bib0067","series-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"10.1016\/j.neunet.2025.108202_bib0068","series-title":"2012 IEEE\/RSJ international conference on intelligent robots and systems","first-page":"5026","article-title":"MuJoCo: A physics engine for model-based control","author":"Todorov","year":"2012"},{"key":"10.1016\/j.neunet.2025.108202_bib0069","series-title":"2018 24\u00feinternational conference on pattern recognition (ICPR)","first-page":"1289","article-title":"Reservoir computing with untrained convolutional neural networks for image recognition","author":"Tong","year":"2018"},{"issue":"5","key":"10.1016\/j.neunet.2025.108202_bib0070","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1103\/PhysRev.36.823","article-title":"On the theory of the brownian motion","volume":"36","author":"Uhlenbeck","year":"1930","journal-title":"Physical Review"},{"key":"10.1016\/j.neunet.2025.108202_bib0071","doi-asserted-by":"crossref","first-page":"43","DOI":"10.58496\/BJN\/2025\/004","article-title":"A comprehensive review on OFDM, 5G and various PAPR minimization techniques based on machine learning","volume":"2025","author":"Vaigandla","year":"2025","journal-title":"Babylonian Journal of Networking"},{"key":"10.1016\/j.neunet.2025.108202_bib0072","first-page":"6000","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"10","key":"10.1016\/j.neunet.2025.108202_bib0073","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-021-3347-8","article-title":"Adaptive deep reinforcement learning for non-stationary environments","volume":"65","author":"Zhu","year":"2022","journal-title":"Science China Information Sciences"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025010834?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025010834?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T20:42:05Z","timestamp":1773261725000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608025010834"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":73,"alternative-id":["S0893608025010834"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108202","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Chaos-based reinforcement learning with TD3","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108202","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108202"}}