{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T06:10:11Z","timestamp":1749276611078,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819665754","type":"print"},{"value":"9789819665761","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\/978-981-96-6576-1_3","type":"book-chapter","created":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T05:38:27Z","timestamp":1749274707000},"page":"26-41","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Interpreting Decision Transformer: Insights from\u00a0Continuous Control Tasks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2010-0631","authenticated-orcid":false,"given":"Dhillu","family":"Thambi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8071-5409","authenticated-orcid":false,"given":"Praveen","family":"Paruchuri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6227-9578","authenticated-orcid":false,"given":"Perusha","family":"Moodley","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,8]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Abnar, S., Zuidema, W.: Quantifying attention flow in transformers. In: Annual Meeting of the Association for Computational Linguistics (2020). https:\/\/api.semanticscholar.org\/CorpusID:218487351","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"3_CR2","doi-asserted-by":"publisher","first-page":"171058","DOI":"10.1109\/ACCESS.2020.3023394","volume":"8","author":"A Alharin","year":"2020","unstructured":"Alharin, A., Doan, T.N., Sartipi, M.: Reinforcement learning interpretation methods: a survey. IEEE Access 8, 171058\u2013171077 (2020)","journal-title":"IEEE Access"},{"key":"3_CR3","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1613\/jair.3912","volume":"47","author":"MG Bellemare","year":"2013","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253\u2013279 (2013)","journal-title":"J. Artif. Intell. Res."},{"key":"3_CR4","unstructured":"Brandfonbrener, D., Bietti, A., Buckman, J., Laroche, R., Bruna, J.: When does return-conditioned supervised learning work for offline reinforcement learning? In: Oh, A.H., Agarwal, A., Belgrave, D., Cho, K. (eds.) Advances in Neural Information Processing Systems (2022). https:\/\/openreview.net\/forum?id=XByg4kotW5"},{"key":"3_CR5","unstructured":"Bricken, T., et\u00a0al.: Towards monosemanticity: decomposing language models with dictionary learning. Trans. Circ. Thread 2 (2023)"},{"key":"3_CR6","unstructured":"Brockman, G., et al.: Openai gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"3_CR7","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR8","doi-asserted-by":"publisher","unstructured":"Cammarata, N., et al.: Thread: circuits. Distill (2020). https:\/\/doi.org\/10.23915\/distill.00024, https:\/\/distill.pub\/2020\/circuits","DOI":"10.23915\/distill.00024"},{"key":"3_CR9","first-page":"15084","volume":"34","author":"L Chen","year":"2021","unstructured":"Chen, L., et al.: Decision transformer: reinforcement learning via sequence modeling. Adv. Neural. Inf. Process. Syst. 34, 15084\u201315097 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR10","unstructured":"Cobbe, K., Klimov, O., Hesse, C., Kim, T., Schulman, J.: Quantifying generalization in reinforcement learning. In: International Conference on Machine Learning, pp. 1282\u20131289. PMLR (2019)"},{"key":"3_CR11","unstructured":"Doshi-Velez, F., Kim, B.: Towards a rigorous science of interpretable machine learning (2017)"},{"key":"3_CR12","unstructured":"Elhage, N., et al.: A mathematical framework for transformer circuits. Trans. Circ. Thread (2021). https:\/\/transformer-circuits.pub\/2021\/framework\/index.html"},{"key":"3_CR13","unstructured":"Emmons, S., Eysenbach, B., Kostrikov, I., Levine, S.: Rvs: what is essential for offline RL via supervised learning? In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=S874XAIpkR-"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Erez, T., Tassa, Y., Todorov, E.: Infinite-horizon model predictive control for periodic tasks with contacts (2012)","DOI":"10.15607\/RSS.2011.VII.010"},{"key":"3_CR15","unstructured":"Fu, J., Kumar, A., Nachum, O., Tucker, G., Levine, S.: D4rl: datasets for deep data-driven reinforcement learning. arXiv preprint arXiv:2004.07219 (2020)"},{"key":"3_CR16","unstructured":"Glanois, C., et al.: A survey on interpretable reinforcement learning. Mach. Learn. 1\u201344 (2024)"},{"key":"3_CR17","unstructured":"Gurnee, W., Nanda, N., Pauly, M., Harvey, K., Troitskii, D., Bertsimas, D.: Finding neurons in a haystack: Case studies with sparse probing. arXiv preprint arXiv:2305.01610 (2023)"},{"issue":"11","key":"3_CR18","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00029","volume":"5","author":"J Hilton","year":"2020","unstructured":"Hilton, J., Cammarata, N., Carter, S., Goh, G., Olah, C.: Understanding rl vision. Distill 5(11), e29 (2020)","journal-title":"Distill"},{"key":"3_CR19","unstructured":"Joseph\u00a0Bloom, P.C.: Decision transformer interpretability. https:\/\/www.lesswrong.com\/posts\/bBuBDJBYHt39Q5zZy\/decision-transformer-interpretability, February 2023"},{"key":"3_CR20","unstructured":"Kenny, E.M., Tucker, M., Shah, J.: Towards interpretable deep reinforcement learning with human-friendly prototypes. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"3_CR21","unstructured":"Levine, S., Kumar, A., Tucker, G., Fu, J.: Offline reinforcement learning: tutorial, review, and perspectives on open problems. arXiv preprint arXiv:2005.01643 (2020)"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"McGrath, T., et al.: Acquisition of chess knowledge in alphazero. Proc. Natl. Acad. Sci. 119(47), e2206625119 (2022)","DOI":"10.1073\/pnas.2206625119"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Milani, S., Topin, N., Veloso, M., Fang, F.: Explainable reinforcement learning: a survey and comparative review. ACM Comput. Surv. (2023)","DOI":"10.1145\/3616864"},{"key":"3_CR24","unstructured":"Nanda, N., Chan, L., Lieberum, T., Smith, J., Steinhardt, J.: Progress measures for grokking via mechanistic interpretability. arXiv preprint arXiv:2301.05217 (2023)"},{"key":"3_CR25","unstructured":"Olah, C.: Mechanistic interpretability, variables, and the importance of interpretable bases. https:\/\/www.transformer-circuits.pub\/2022\/mech-interp-essay\/index.html (2022), Accessed 25 Apr 2024"},{"key":"3_CR26","unstructured":"Prudencio, R.F., Maximo, M.R., Colombini, E.L.: A survey on offline reinforcement learning: taxonomy, review, and open problems. IEEE Trans. Neural Netw. Learn. Syst. (2023)"},{"key":"3_CR27","unstructured":"Raghu, A., Komorowski, M., Ahmed, I., Celi, L.A., Szolovits, P., Ghassemi, M.: Deep reinforcement learning for sepsis treatment. CoRR abs\/1711.09602 (2017), http:\/\/arxiv.org\/abs\/1711.09602"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: Mujoco: a physics engine for model-based control. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 5026\u20135033. IEEE (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"3_CR29","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"3_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1007\/978-3-642-04921-7_39","volume-title":"Adaptive and Natural Computing Algorithms","author":"P Wawrzy\u0144ski","year":"2009","unstructured":"Wawrzy\u0144ski, P.: A cat-like robot real-time learning to run. In: Kolehmainen, M., Toivanen, P., Beliczynski, B. (eds.) ICANNGA 2009. LNCS, vol. 5495, pp. 380\u2013390. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-04921-7_39"},{"key":"3_CR31","unstructured":"Wolf, T., et\u00a0al.: transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345 (2020)"},{"key":"3_CR32","unstructured":"Wu, Y.H., Wang, X., Hamaya, M.: Elastic decision transformer. ArXiv abs\/2307.02484 (2023), https:\/\/api.semanticscholar.org\/CorpusID:259342857"},{"key":"3_CR33","doi-asserted-by":"publisher","unstructured":"Yu, C., Liu, J., Nemati, S., Yin, G.: Reinforcement learning in healthcare: a survey. ACM Comput. Surv. 55(1) (2021). https:\/\/doi.org\/10.1145\/3477600","DOI":"10.1145\/3477600"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-6576-1_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T05:38:41Z","timestamp":1749274721000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-6576-1_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819665754","9789819665761"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-6576-1_3","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":"8 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"}}]}}