{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T21:54:07Z","timestamp":1770069247786,"version":"3.49.0"},"reference-count":25,"publisher":"Elsevier","isbn-type":[{"value":"9781558603356","type":"print"}],"license":[{"start":{"date-parts":[[1994,1,1]],"date-time":"1994-01-01T00:00:00Z","timestamp":757382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[1994]]},"DOI":"10.1016\/b978-1-55860-335-6.50030-1","type":"book-chapter","created":{"date-parts":[[2014,7,1]],"date-time":"2014-07-01T02:59:18Z","timestamp":1404183558000},"page":"181-189","source":"Crossref","is-referenced-by-count":171,"title":["Reward Functions for Accelerated Learning"],"prefix":"10.1016","author":[{"given":"Maja J","family":"Mataric","sequence":"first","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/B978-1-55860-335-6.50030-1_bib1","series-title":"\u2018Designing Autonomous Agents: Theory and Practice from Biology to Engineering and Back\u2019","first-page":"17","article-title":"What Are Plans for?","author":"Agre","year":"1990"},{"key":"10.1016\/B978-1-55860-335-6.50030-1_bib2","unstructured":"Atkeson, C. G. (1990), Memory-Based Approaches to Approximating Continuous Functions, in \u2018Proceedings, Sixt Yale Workshop on Adaptive and Learning Systems\u2019."},{"key":"10.1016\/B978-1-55860-335-6.50030-1_bib3","article-title":"\u2018Learning to Act using Real-Time Dynamic Programming\u2019","author":"Barto","year":"1993","journal-title":"AI Journal"},{"key":"10.1016\/B978-1-55860-335-6.50030-1_bib4","doi-asserted-by":"crossref","unstructured":"Brooks, R. A. (1990), The Behavior Language; User's Guide, Technical Report AIM-1127, MIT Artificial Intelligence Lab.","DOI":"10.21236\/ADA225808"},{"key":"10.1016\/B978-1-55860-335-6.50030-1_bib5","series-title":"\u2018Robot Learning\u2019","first-page":"193","article-title":"Real Robots, Real Learning Problems","author":"Brooks","year":"1992"},{"key":"10.1016\/B978-1-55860-335-6.50030-1_bib6","unstructured":"Chapman, D. & Kaelbling, L. P. (1991), Input Generalization in Delayed Reinforcement Learning: An Algorithm and Performance Comparisons, in \u2018Proceedings, IJCAI-91\u2019, Sydney, Australia."},{"key":"10.1016\/B978-1-55860-335-6.50030-1_bib7","article-title":"\u2018On the Convergence of Stochastic Iterative Dynamic Programming Algorithms\u2019","author":"Jaakkola","year":"1993","journal-title":"Submitted to Neural Computation"},{"key":"10.1016\/B978-1-55860-335-6.50030-1_bib8","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1207\/s15516709cog1603_1","article-title":"\u2018Forward Models: Supervised Learning with a Distal Teacher\u2019","volume":"16","author":"Jordan","year":"1992","journal-title":"Cognitive Science"},{"key":"10.1016\/B978-1-55860-335-6.50030-1_bib9","unstructured":"Kaelbling, L. P. (1990), Learning in Embedded Systems, PhD thesis, Stanford University."},{"key":"10.1016\/B978-1-55860-335-6.50030-1_bib10","unstructured":"Maes, P. & Brooks, R. A. (1990), Learning to Coordinate Behaviors, in \u2018Proceedings, AAAI-91\u2019, Boston, MA, pp. 796\u2013802."},{"key":"10.1016\/B978-1-55860-335-6.50030-1_bib11","unstructured":"Mahadevan, S. & Connell, J. (1991), Automatic Programming of Behavior-based Robots using Reinforcement Learning, in \u2018Proceedings, AAAI-91\u2019, Pittsburgh, PA, pp. 8\u201314."},{"key":"10.1016\/B978-1-55860-335-6.50030-1_bib12","doi-asserted-by":"crossref","unstructured":"Matari\u0107, M. J. (1992), Designing Emergent Behaviors: From Local Interactions to Collective Intelligence, in \u2018From Animals to Animats: International Conference on Simulation of Adaptive Behavior\u2019.","DOI":"10.7551\/mitpress\/3116.003.0059"},{"key":"10.1016\/B978-1-55860-335-6.50030-1_bib13","unstructured":"Matari\u00e9, M. J. (1993), Kin Recognition, Similarity, and Group Behavior, in \u2018Proceedings of the Fifteenth Annual Conference of the Cognitive Science Society\u2019, Boulder, Colorado, pp. 705\u2013710."},{"key":"10.1016\/B978-1-55860-335-6.50030-1_bib14","doi-asserted-by":"crossref","unstructured":"Matari\u00e9, M. J. (1994), Interaction and Intelligent Behavior, PhD thesis, MIT.","DOI":"10.21236\/ADA290049"},{"key":"10.1016\/B978-1-55860-335-6.50030-1_bib15","doi-asserted-by":"crossref","DOI":"10.1109\/37.257895","article-title":"\u2018Robot Juggling: An Implementation of Memory-Based Learning\u2019","author":"Schaal","year":"1994","journal-title":"Control Systems Magazine"},{"key":"10.1016\/B978-1-55860-335-6.50030-1_bib16","unstructured":"Singh, S. P. (1991), Transfer of Learning Across Compositions of Sequential Tasks, in \u2018Proceedings, Eighth International Conference on Machine Learning\u2019, Morgan Kaufmann, Evanston, Illinois, pp. 348\u2013352."},{"issue":"1","key":"10.1016\/B978-1-55860-335-6.50030-1_bib17","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1007\/BF00115009","article-title":"\u2018Learning to Predict by Method of Temporal Differences\u2019","volume":"3","author":"Sutton","year":"1988","journal-title":"The Journal of Machine Learning"},{"key":"10.1016\/B978-1-55860-335-6.50030-1_bib18","doi-asserted-by":"crossref","unstructured":"Sutton, R. S. (1990), Integrated Architectures for Learning, Planning and Reacting Based on Approximating Dynamic Programming, in \u2018Proceedings, Seventh International Conference on Machine Learning\u2019, Austin, Texas.","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"10.1016\/B978-1-55860-335-6.50030-1_bib19","unstructured":"Tan, M. (1993), Multi-Agent Reinforcement Learning: Independent vs. Cooperative Agents, in \u2018Proceedings, Tenth International Conference on Machine Learning\u2019, Amherst, MA, pp. 330\u2013337."},{"key":"10.1016\/B978-1-55860-335-6.50030-1_bib20","series-title":"\u2018Advances in Neural Information Processing Systems 4\u2019","first-page":"259","article-title":"Practical Issues in Temporal Difference Learning","author":"Tesauro","year":"1992"},{"key":"10.1016\/B978-1-55860-335-6.50030-1_bib21","unstructured":"Watkins, C. J. C. H. (1989), Learning from Delayed Rewards, PhD thesis, King's College, Cambridge."},{"key":"10.1016\/B978-1-55860-335-6.50030-1_bib22","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"\u2018Q-Learning\u2019","volume":"8","author":"Watkins","year":"1992","journal-title":"Machine Learning"},{"key":"10.1016\/B978-1-55860-335-6.50030-1_bib23","unstructured":"Whitehead, S. D. (1992), Reinforcement Learning for the Adaptive Control of Perception and Action, PhD thesis, University of Rochester."},{"key":"10.1016\/B978-1-55860-335-6.50030-1_bib24","doi-asserted-by":"crossref","unstructured":"Whitehead, S. D. & Ballard, D. H. (1990), Active Perception and Reinforcement Learning, in \u2018Proceedings, Seventh International Conference on Machine Learning\u2019, Austin, Texas.","DOI":"10.1016\/B978-1-55860-141-3.50025-0"},{"key":"10.1016\/B978-1-55860-335-6.50030-1_bib25","series-title":"\u2018Robot Learning\u2019","first-page":"45","article-title":"Learning Multiple Goal Behavior via Task Decomposition and Dynamic Policy Merging","author":"Whitehead","year":"1993"}],"container-title":["Machine Learning Proceedings 1994"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:B9781558603356500301?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:B9781558603356500301?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,5,28]],"date-time":"2024-05-28T10:42:50Z","timestamp":1716892970000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/B9781558603356500301"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1994]]},"ISBN":["9781558603356"],"references-count":25,"URL":"https:\/\/doi.org\/10.1016\/b978-1-55860-335-6.50030-1","relation":{},"subject":[],"published":{"date-parts":[[1994]]}}}