{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T04:02:40Z","timestamp":1750737760205,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":19,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819665785","type":"print"},{"value":"9789819665792","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-6579-2_11","type":"book-chapter","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T12:06:34Z","timestamp":1750680394000},"page":"151-165","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Virtual Command Allocation: Enhancing Hexapod Robot Locomotion Through Goal-Conditioned Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3042-8267","authenticated-orcid":false,"given":"Takanori","family":"Hashimoto","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6503-5907","authenticated-orcid":false,"given":"Teijiro","family":"Isokawa","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7388-7624","authenticated-orcid":false,"given":"Naotake","family":"Kamiura","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,24]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Lewis, A., Fagg, H., Bekey, A.: Genetic algorithms for gait synthesis in a hexapod robot. In: Recent trends in mobile robots, pp. 317\u2013331. World Scientific, (1993)","DOI":"10.1142\/9789814354301_0011"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Lee, T., Liao, M., Chen, K.: On the stability properties of hexapod tripod gait. IEEE J. Robot. Autom. 4(4), 427\u2013434 IEEE (1988)","DOI":"10.1109\/56.808"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Ding, X., Wang, Z., Rovetta, A., Zhu, M.: Locomotion analysis of hexapod robot, climbing and walking robots, vol. 28, pp. 291\u2013310. In: Tech Rijeka, Croatia (2010)","DOI":"10.5772\/8822"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y. : MuJoCo: a physics engine for model-based control. In: IEEE\/RSJ, pp. 5026\u20135033 (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"11_CR5","unstructured":"Kingma, P., Ba, J. : Adam: a method for stochastic optimization. In: ICLR, pp. 1\u201315 (2015)"},{"key":"11_CR6","unstructured":"Lillicrap, P., et al.: Continuous control with deep reinforcement learning, arXiv preprint arXiv:1509.02971, (2015)"},{"key":"11_CR7","unstructured":"Andrychowicz, M., et al.: Hindsight experience replay. In: NeurIPS, vol. 30, pp. 5048\u20135058 (2017)"},{"key":"11_CR8","unstructured":"Fujimoto, S., Hoof, H., Meger, D. : Addressing function approximation error in actor-critic methods. In: ICML, vol. 80, pp. 1587\u20131596, PMLR (2018)"},{"key":"11_CR9","unstructured":"Bradbury, J., et al.: JAX: composable transformations of Python+NumPy programs. http:\/\/github.com\/google\/jax (2018)"},{"key":"11_CR10","unstructured":"Trott, A., Zheng, S., Xiong, C., Socher, R.: Keeping your distance: solving sparse reward tasks using self-balancing shaped rewards. In: NeurIPS vol. 32, pp. 10376\u201310386 (2019)"},{"key":"11_CR11","unstructured":"Babuschkin, I., et al.: The DeepMind JAX Ecosystem. http:\/\/github.com\/google-deepmind (2020)"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Memarian, F., Goo, W., Lioutikov, R., Niekum, S., Topcu, U.: Self-supervised online reward shaping in sparse-reward environments. In: IROS, pp. 2369\u20132375, IEEE, (2021)","DOI":"10.1109\/IROS51168.2021.9636020"},{"key":"11_CR13","unstructured":"Hansen, N., Wang, X., Su, H. : Temporal difference learning for model predictive control. In: ICML, vol. 162, pp. 8387\u20138406, PMLR (2022)"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Liu, M., Zhu, M., Zhang, W.: Goal-conditioned reinforcement learning: problems and solutions. In: IJCAI, pp. 5502\u20135511 (2022)","DOI":"10.24963\/ijcai.2022\/770"},{"key":"11_CR15","unstructured":"Devidze, R., Kamalaruban, P., Singla, A.: Exploration-guided reward shaping for reinforcement learning under sparse rewards. In: NeurIPS, vol. 35, pp. 5829\u20135842 (2022)"},{"key":"11_CR16","unstructured":"Heek, J., et al.: Flax: A neural network library and ecosystem for JAX. http:\/\/github.com\/google\/flax (2023)"},{"key":"11_CR17","unstructured":"Toledo, E., et al.: Flashbax: streamlining experience replay buffers for reinforcement learning with JAX. https:\/\/github.com\/instadeepai\/flashbax (2023)"},{"key":"11_CR18","unstructured":"MakeYourPet. : Hexapod. https:\/\/github.com\/MakeYourPet\/hexapod (2023)"},{"key":"11_CR19","unstructured":"Hansen, N., Su, H., Wang, X. : TD-MPC2: Scalable, robust world models for continuous control. In: ICLR, pp. 1\u201330 (2024)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-6579-2_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T12:06:41Z","timestamp":1750680401000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-6579-2_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819665785","9789819665792"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-6579-2_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"24 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2024.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}