{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T16:49:11Z","timestamp":1793206151511,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2007,6,20]],"date-time":"2007-06-20T00:00:00Z","timestamp":1182297600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2007,6,20]]},"DOI":"10.1145\/1273496.1273572","type":"proceedings-article","created":{"date-parts":[[2008,10,7]],"date-time":"2008-10-07T13:06:52Z","timestamp":1223384812000},"page":"601-608","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":62,"title":["Automatic shaping and decomposition of reward functions"],"prefix":"10.1145","author":[{"given":"Bhaskara","family":"Marthi","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology, Cambridge, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2007,6,20]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"AAAI","author":"Agogino A.","year":"2006"},{"key":"e_1_3_2_1_2_1","volume-title":"ICML","author":"Alstrom J. R. P.","year":"1998"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the 17th National Conference on Artificial Intelligence (pp. 119--125)","author":"Andre D.","year":"2002"},{"key":"e_1_3_2_1_4_1","unstructured":"Bagnell J. & Ng A. (2006). On local rewards and scaling distributed reinforcement learning. Neural Information Processing Systems. MIT Press.  Bagnell J. & Ng A. (2006). On local rewards and scaling distributed reinforcement learning. Neural Information Processing Systems . MIT Press."},{"key":"e_1_3_2_1_5_1","unstructured":"Bertsekas D. P. & Tsitsiklis J. N. (1996). Neuro-dynamic programming. Athena Scientific.   Bertsekas D. P. & Tsitsiklis J. N. (1996). Neuro-dynamic programming . Athena Scientific."},{"key":"e_1_3_2_1_6_1","unstructured":"Chang Y.-H. Ho T. & Kaelbling L. P. (2004). All learning is local: Multi-agent learning in global reward games. In S. Thrun L. Saul and B. Sch\u00f6lkopf (Eds.) Advances in neural information processing systems 16. Cambridge MA: MIT Press.  Chang Y.-H. Ho T. & Kaelbling L. P. (2004). All learning is local: Multi-agent learning in global reward games. In S. Thrun L. Saul and B. Sch\u00f6lkopf (Eds.) Advances in neural information processing systems 16 . Cambridge MA: MIT Press."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Chow C. & Tsitsiklis J. (1991). An optimal one-way multigrid algorithm for discrete-time stochastic control. IEEE transactions on automatic control 36 898--914.  Chow C. & Tsitsiklis J. (1991). An optimal one-way multigrid algorithm for discrete-time stochastic control. IEEE transactions on automatic control 36 898--914.","DOI":"10.1109\/9.133184"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Dietterich T. G. (2000). Hierarchical reinforcement learning with the MAXQ value function decomposition. JAIR 13.   Dietterich T. G. (2000). Hierarchical reinforcement learning with the MAXQ value function decomposition. JAIR 13 .","DOI":"10.1613\/jair.639"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Guestrin C. Koller D. Parr R. & Venkataraman S. (2003). Efficient solution algorithms for factored MDPs. JAIR 19.   Guestrin C. Koller D. Parr R. & Venkataraman S. (2003). Efficient solution algorithms for factored MDPs. JAIR 19 .","DOI":"10.1613\/jair.1000"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/2074094.2074120"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143906"},{"key":"e_1_3_2_1_12_1","unstructured":"Laud A. & DeJong G. (2002). Reinforcement learning and shaping: Encouraging intended behaviors. ICML (pp. 355--362).   Laud A. & DeJong G. (2002). Reinforcement learning and shaping: Encouraging intended behaviors. ICML (pp. 355--362)."},{"key":"e_1_3_2_1_13_1","volume-title":"ICML","author":"Laud A.","year":"2003"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the ninth international symposium on AI and mathematics.","author":"Li L.","year":"2006"},{"key":"e_1_3_2_1_15_1","volume-title":"echnical Report)","author":"Littman M.","year":"1993"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Marthi B. (2007). Automatic shaping and decomposition of reward functions: website. http:\/\/people.csail.mit.edu\/bhaskara\/autoshape\/.  Marthi B. (2007). Automatic shaping and decomposition of reward functions: website. http:\/\/people.csail.mit.edu\/bhaskara\/autoshape\/.","DOI":"10.1145\/1273496.1273572"},{"key":"e_1_3_2_1_17_1","volume-title":"IJCAI","author":"Marthi B.","year":"2005"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50030-1"},{"key":"e_1_3_2_1_19_1","volume-title":"ICML","author":"Ng A.","year":"1999"},{"key":"e_1_3_2_1_20_1","volume-title":"ICML","author":"Russell S.","year":"2003"},{"key":"e_1_3_2_1_21_1","volume-title":"ICML 1999 (pp. 371--378)","author":"Schneider J.","year":"1999"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022693225949"},{"key":"e_1_3_2_1_23_1","volume-title":"echnical Report). MIT.","author":"Steinkraus K.","year":"2004"},{"key":"e_1_3_2_1_24_1","volume-title":"ICML","author":"Stone P.","year":"2001"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"e_1_3_2_1_26_1","volume-title":"echnical Report)","author":"VanEck N.","year":"2005"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622434.1622441"},{"key":"e_1_3_2_1_28_1","volume-title":"UAI","author":"Yoon S. W.","year":"2002"}],"event":{"name":"ICML '07 & ILP '07: The 24th Annual International Conference on Machine Learning held in conjunction with the 2007 International Conference on Inductive Logic Programming","location":"Corvalis Oregon USA","acronym":"ICML '07 & ILP '07","sponsor":["Machine Learning Journal"]},"container-title":["Proceedings of the 24th international conference on Machine learning"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1273496.1273572","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1273496.1273572","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T14:58:01Z","timestamp":1750258681000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1273496.1273572"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,6,20]]},"references-count":28,"alternative-id":["10.1145\/1273496.1273572","10.1145\/1273496"],"URL":"https:\/\/doi.org\/10.1145\/1273496.1273572","relation":{},"subject":[],"published":{"date-parts":[[2007,6,20]]},"assertion":[{"value":"2007-06-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}