{"type":"ScholarlyArticle","title":"Model-free, Model-based, and General Intelligence","authors":[{"name":"Hector Geffner","slug":"hector-geffner","given":"Hector","family":"Geffner","affiliation":"Universitat Pompeu Fabra , Roc Boronat 138 , 08032 Barcelona , Spain; ICREA , Pg. Lluís Companys 23 , 08010 Barcelona , Spain"}],"abstract":"During the 60s and 70s, AI researchers explored intuitions about intelligence by writing programs that displayed intelligent behavior. Many good ideas came out from this work  but  programs written by hand were not robust or general. After the 80s, research  increasingly shifted  to the development of learners capable of inferring  behavior and functions from experience and data, and solvers capable of tackling well-defined but intractable models like SAT, classical planning, Bayesian networks, and POMDPs. The learning approach has achieved considerable success but results in black boxes that do not have the flexibility, transparency, and generality of their model-based counterparts. Model-based approaches, on the other hand, require models and scalable algorithms. Model-free learners  and model-based solvers  have indeed close parallels with Systems 1 and 2 in current theories of the human mind: the first, a fast, opaque, and inflexible intuitive mind; the second,  a slow, transparent, and flexible analytical mind. In this paper, I review developments in AI and draw on these theories  to  discuss  the gap between model-free learners and model-based solvers, a gap that  needs to be bridged in order to have intelligent systems that are robust and general.","doi":"10.24963/ijcai.2018/2","url":"https://ijcai.org/proceedings/2018/2","pdf":"https://ijcai.org/proceedings/2018/0002.pdf","markdown":"https://ijcai.org/proceedings/2018/2.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/2","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Invited Speakers","track":"Invited Speakers","number":2,"pages":{"first":10,"last":17},"keywords":["Planning and Scheduling: Planning Algorithms","Knowledge Representation and Reasoning: Common-Sense Reasoning","Humans and AI: Cognitive Modeling","Machine Learning: Machine Learning"],"videos":[],"references":[{"position":1,"raw":"[Anthony et al., 2017] T. Anthony, Z. Tian, and D. Barber. Thinking fast and slow with deep learning and tree search. In NIPS, 2017.","title":"Thinking fast and slow with deep learning and tree search","authors":"T Anthony, Z Tian, D Barber","year":"2017","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bandres et al., 2018] W. Bandres, B. Bonet, and H. Geffner. Planning with pixels in (almost) real time. In AAAI, 2018.","title":"Planning with pixels in (almost) real time","authors":"W Bandres, B Bonet, H Geffner","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bertsekas, 1995] D. Bertsekas. Dynamic Programming and Optimal Control, Vols 1 and 2. Athena Scientific, 1995.","title":"Dynamic Programming and Optimal Control, Vols 1 and 2","authors":"D Bertsekas","year":"1995","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bertsekas, 2018] D. Bertsekas. Feature-based aggregation and deep reinforcement learning: A survey and some new implementations. arXiv preprint arXiv:1804.04577, 2018.","title":"Feature-based aggregation and deep reinforcement learning: A survey and some new implementations","authors":"D Bertsekas","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Biere et al., 2009] A. Biere, M. Heule, H. van Maaren, and T. Walsh, editors. Handbook of Satisfiability: Volume 185 Frontiers in Artificial Intelligence and Applications. IOS Press, 2009.","title":"Handbook of Satisfiability: Volume 185 Frontiers in Artificial Intelligence and Applications","authors":null,"year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Bonet and Geffner, 2001] B. Bonet and H. Geffner. Plan- ning as heuristic search. Artificial Intelligence, 129(1- 2):5-33, 2001.","title":"Planning as heuristic search","authors":"B Bonet, H Geffner","year":"2001","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Bonet and Geffner, 2014] B. Bonet and H. Geffner. Flexi- ble and scalable partially observable planning with linear translations. In Proc. AAAI, 2014.","title":"Flexible and scalable partially observable planning with linear translations","authors":"B Bonet, H Geffner","year":"2014","venue":"Proc. AAAI","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Bonet and Geffner, 2018] B. Bonet and H. Geffner. Fea- tures, projections, and representation change for general- ized planning. arXiv preprint arXiv:1801.10055, 2018.","title":"Features, projections, and representation change for generalized planning","authors":"B Bonet, H Geffner","year":"2018","venue":null,"doi":null,"url":null,"internal_url":"/proceedings/2018/649"},{"position":9,"raw":"[Bonet et al., 2009] B. Bonet, H. Palacios, and H. Geffner. Automatic derivation of memoryless policies and finite- state controllers using classical planners. In Proc. ICAPS- 09, pages 34-41, 2009.","title":"Automatic derivation of memoryless policies and finitestate controllers using classical planners","authors":"B Bonet, H Palacios, H Geffner","year":"2009","venue":"Proc. ICAPS-09","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Bonet et al., 2017] B. Bonet, G. De Giacomo, H. Geffner, and S. Rubin. Generalized planning: non-deterministic ab- stractions and trajectory constraints. In Proc. IJCAI, 2017.","title":"Generalized planning: non-deterministic abstractions and trajectory constraints","authors":"B Bonet, G De Giacomo, H Geffner, S Rubin","year":"2017","venue":"Proc. IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/121"},{"position":11,"raw":"[Camacho et al., 2017] A. Camacho, E. Triantafillou, C. Muise, J. Baier, and S. McIlraith. Non-deterministic planning with temporally extended goals: LTL over finite and infinite traces. In Proc. AAAI, 2017.","title":"Non-deterministic planning with temporally extended goals: LTL over finite and infinite traces","authors":"A Camacho, E Triantafillou, C Muise, J Baier, S Mcilraith","year":"2017","venue":"Proc. AAAI","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Charniak et al., 1980] E. Charniak, C. Riesbeck, and D. McDermott. Artificial intelligence programming. L. Erlbaum Associates, 1980.","title":"Artificial intelligence programming","authors":"E Charniak, C Riesbeck, D Mcdermott","year":"1980","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Chatterjee et al., 2016] K. Chatterjee, M. Chmelik, and J. Davies. A symbolic SAT-based algorithm for almost- sure reachability with small strategies in POMDPs. In Proc AAAI, 2016.","title":"A symbolic SAT-based algorithm for almostsure reachability with small strategies in POMDPs","authors":"K Chatterjee, M Chmelik, J Davies","year":"2016","venue":"Proc AAAI","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Coulom, 2006] R. Coulom. Efficient selectivity and backup operators in Monte-Carlo tree search. In Proc. Int. Con- ference on Computers and Games, pages 72-83. Springer, 2006.","title":"Efficient selectivity and backup operators in Monte-Carlo tree search","authors":"R Coulom","year":"2006","venue":"Proc. Int. Conference on Computers and Games","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Darwiche, 2017] A Darwiche. Human-level intelligence or animal-like abilities? arXiv preprint, 2017.","title":"Human-level intelligence or animal-like abilities?","authors":"Darwiche","year":"2017","venue":"A Darwiche","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Dechter, 2003] R. Dechter. Constraint Processing. Morgan Kaufmann, 2003.","title":"Constraint Processing","authors":"R Dechter","year":"2003","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Dietterich, 2018] T. Dietterich. Reflections on innateness in machine learning. https://medium.com/@tdietterich, 2018.","title":"Reflections on innateness in machine learning","authors":"T Dietterich","year":null,"venue":null,"doi":null,"url":"https://medium.com/@tdietterich,2018","internal_url":null},{"position":18,"raw":"[Evans and Stanovich, 2013] J. Evans and K. Stanovich. Dual-process theories of higher cognition: Advancing the debate. Perspectives on psychological science, 8(3), 2013.","title":"Dual-process theories of higher cognition: Advancing the debate","authors":"J Evans, K Stanovich","year":"2013","venue":"Perspectives on psychological science","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Feigenbaum and Feldman, 1963] E.A. Feigenbaum and J. Feldman. Computers and thought. McGraw-Hill, 1963.","title":"Computers and thought","authors":"E A Feigenbaum, J Feldman","year":"1963","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Francès et al., 2017] G. Francès, M. Ramírez, N. Lipovet- zky, and H. Geffner. Purely declarative action representa- tions are overrated: Classical planning with simulators. In Proc. IJCAI, 2017.","title":"Purely declarative action representations are overrated: Classical planning with simulators","authors":"G Francès, M Ramírez, N Lipovetzky, H Geffner","year":"2017","venue":"Proc. IJCAI","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Gebser et al., 2012] M. Gebser, R. Kaminski, B. Kaufmann, and T. Schaub. Answer set solving in practice. Morgan & Claypool, 2012.","title":"Answer set solving in practice","authors":"M Gebser, R Kaminski, B Kaufmann, T Schaub","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Geffner and Bonet, 2013] H. Geffner and B. Bonet. A con- cise introduction to models and methods for automated planning. Morgan & Claypool, 2013.","title":"A concise introduction to models and methods for automated planning","authors":"H Geffner, B Bonet","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Geffner, 2010] H. Geffner. Heuristics, planning and cogni- tion. In J. Halpern R. Dechter, H. Geffner, editor, Heuris- tics, Probability and Causality. A Tribute to Judea Pearl. College Publications, 2010.","title":"Heuristics, planning and cognition","authors":"H Geffner","year":"2010","venue":"Heuristics, Probability and Causality. A Tribute to Judea Pearl","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Genesereth et al., 2005] M. Genesereth, N. Love, and B. Pell. General game playing: Overview of the AAAI competition. AI magazine, 26(2):62, 2005.","title":"General game playing: Overview of the AAAI competition","authors":"M Genesereth, N Love, B Pell","year":"2005","venue":"AI magazine","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Graves et al., 2013] A. Graves, A. Mohamed, and G. Hin- ton. Speech recognition with deep recurrent neural net- works. In Proc. ICASSP, pages 6645-6649, 2013.","title":"Speech recognition with deep recurrent neural networks","authors":"A Graves, A Mohamed, G Hinton","year":"2013","venue":"Proc. ICASSP","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Graves et al., 2014] A. Graves, G. Wayne, and I. Danihelka. Neural Turing machines. arXiv preprint arXiv:1410.5401, 2014.","title":"Neural Turing machines","authors":"A Graves, G Wayne, I Danihelka","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Groshev et al., 2017] E. Groshev, A. Tamar, S. Srivas- tava, and P. Abbeel. Learning generalized reactive policies using deep neural networks. arXiv preprint arXiv:1708.07280, 2017.","title":"Learning generalized reactive policies using deep neural networks","authors":"E Groshev, A Tamar, S Srivastava, P Abbeel","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Heath, 2014] J. Heath. Enlightenment 2.0. Harper Collins, 2014.","title":"Enlightenment 2.0","authors":"J Heath","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Hoffmann and Nebel, 2001] J. Hoffmann and B. Nebel. The FF planning system: Fast plan generation through heuris- tic search. JAIR, 14:253-302, 2001.","title":"The FF planning system: Fast plan generation through heuristic search","authors":"Hoffmann, ] J Nebel, B Hoffmann, Nebel","year":"2001","venue":"JAIR","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Hu and De Giacomo, 2011] Y. Hu and G. De Giacomo. Generalized planning: Synthesizing plans that work for multiple environments. In Proc. IJCAI, 2011.","title":"Generalized planning: Synthesizing plans that work for multiple environments","authors":"Y Hu, G De Giacomo","year":"2011","venue":"Proc. IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2011/159"},{"position":31,"raw":"[Kaelbling et al., 1998] L. Kaelbling, M. Littman, and T. Cassandra. Planning and acting in partially observable stochastic domains. AI, 101(1-2):99-134, 1998.","title":"Planning and acting in partially observable stochastic domains","authors":"L Kaelbling, M Littman, T Cassandra","year":"1998","venue":"AI","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Kahneman, 2011] D. Kahneman. Thinking, fast and slow. Farrar, Straus and Giroux, 2011.","title":"Thinking, fast and slow","authors":"D Kahneman","year":"2011","venue":null,"doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Kautz and Selman, 1996] H. Kautz and B. Selman. Pushing the envelope: Planning, propositional logic, and stochastic search. In Proc. AAAI, pages 1194-1201, 1996.","title":"Pushing the envelope: Planning, propositional logic, and stochastic search","authors":"H Kautz, B Selman","year":"1996","venue":"Proc. AAAI","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Kaye, 2000] R. Kaye. Minesweeper is NP-Complete. Math- ematical Intelligencer, 22(2):9-15, 2000.","title":"Minesweeper is NP-Complete","authors":"R Kaye","year":"2000","venue":"Mathematical Intelligencer","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Kocsis and Szepesvári, 2006] L. Kocsis and C. Szepesvári. Bandit based Monte-Carlo planning. In Proc. ECML- 2006, pages 282-293, 2006.","title":"Bandit based Monte-Carlo planning","authors":"L Kocsis, C Szepesvári","year":"2006","venue":"Proc. ECML-2006","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Krizhevsky et al., 2012] A. Krizhevsky, I. Sutskever, and G. Hinton. Imagenet classification with deep convolu- tional neural networks. In NIPS, 2012.","title":"Imagenet classification with deep convolutional neural networks","authors":"A Krizhevsky, I Sutskever, G Hinton","year":"2012","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Lake et al., 2017] B. Lake, T. Ullman, J. Tenenbaum, and S. Gershman. Building machines that learn and think like people. Behavioral and Brain Sciences, 40, 2017.","title":"Building machines that learn and think like people","authors":"B Lake, T Ullman, J Tenenbaum, S Gershman","year":"2017","venue":"Behavioral and Brain Sciences","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[LeCun et al., 1989] Y. LeCun, B. Boser, J. Denker, D. Hen- derson, R. Howard, W. Hubbard, and L. Jackel. Back- propagation applied to handwritten zip code recognition. Neural computation, 1(4):541-551, 1989.","title":"Backpropagation applied to handwritten zip code recognition","authors":"Y Lecun, B Boser, J Denker, D Henderson, R Howard, W Hubbard, L Jackel","year":"1989","venue":"Neural computation","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[LeCun et al., 2015] Y. LeCun, Y. Bengio, and G. Hinton. Deep learning. Nature, 521(7553):436, 2015.","title":"Deep learning","authors":"Y Lecun, Y Bengio, G Hinton","year":"2015","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Lenat et al., 1990] D. Lenat, R. Guha, K. Pittman, D. Pratt, and M. Shepherd. CYC: toward programs with common sense. Communications of the ACM, 33(8):30-49, 1990.","title":"CYC: toward programs with common sense","authors":"D Lenat, R Guha, K Pittman, D Pratt, M Shepherd","year":"1990","venue":"Communications of the ACM","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Liang et al., 2016] Y. Liang, M. Machado, E. Talvitie, and M. Bowling. State of the art control of Atari games using shallow reinforcement learning. In Proc. AAMAS, 2016.","title":"State of the art control of Atari games using shallow reinforcement learning","authors":"Y Liang, M Machado, E Talvitie, M Bowling","year":"2016","venue":"Proc. AAMAS","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Lipovetzky and Geffner, 2012] N. Lipovetzky and H. Gef- fner. Width and serialization of classical planning prob- lems. In Proc. ECAI, 2012.","title":"Width and serialization of classical planning problems","authors":"N Lipovetzky, H Geffner","year":"2012","venue":"Proc. ECAI","doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Lipovetzky and Geffner, 2017] N. Lipovetzky and H. Gef- fner. Best-first width search: Exploration and exploitation in classical planning. In Proc. AAAI, 2017.","title":"Best-first width search: Exploration and exploitation in classical planning","authors":"N Lipovetzky, H Geffner","year":"2017","venue":"Proc. AAAI","doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Lipovetzky et al., 2015] N. Lipovetzky, M. Ramirez, and H. Geffner. Classical planning with simulators: Results on the atari video games. In Proc. IJCAI, 2015.","title":"Classical planning with simulators: Results on the atari video games","authors":"N Lipovetzky, M Ramirez, H Geffner","year":"2015","venue":"Proc. IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2015/230"},{"position":45,"raw":"[Marcus, 2018a] G. Marcus. Innateness, AlphaZero, and ar- tificial intelligence. arXiv preprint, 2018.","title":"Innateness, AlphaZero, and artificial intelligence","authors":"; G Marcus, Marcus","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Marcus, 2018b] Gary Marcus. Deep learning: A critical ap- praisal. arXiv preprint arXiv:1801.00631, 2018.","title":"Deep learning: A critical appraisal","authors":"Gary Marcus, Marcus","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":47,"raw":"[McCarthy, 1958] J. McCarthy. Programs with common sense. In Proc. Symp. on Mechanization of Thought Pro- cesses, 1958.","title":"Programs with common sense","authors":"J Mccarthy","year":"1958","venue":"Proc. Symp. on Mechanization of Thought Processes","doi":null,"url":null,"internal_url":null},{"position":48,"raw":"[McCarthy, 1987] J. McCarthy. Generality in artificial intel- ligence. Communications of the ACM, 30(12), 1987.","title":"Generality in artificial intelligence","authors":"J Mccarthy","year":"1987","venue":"Communications of the ACM","doi":null,"url":null,"internal_url":null},{"position":49,"raw":"[McDermott, 1999] D. McDermott. Using regression-match graphs to control search in planning. Artificial Intelli- gence, 109(1-2):111-159, 1999.","title":"Using regression-match graphs to control search in planning","authors":"D Mcdermott","year":"1999","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":50,"raw":"[Mnih et al., 2015] V. Mnih, K. Kavukcuoglu, D. Silver, A. A Rusu, J. Veness, M. G Bellemare, A. Graves, M. Riedmiller, A. K Fidjeland, G. Ostrovski, et al. Human- level control through deep reinforcement learning. Nature, 518(7540):529, 2015.","title":"Humanlevel control through deep reinforcement learning","authors":"V Mnih, K Kavukcuoglu, D Silver, A Rusu, J Veness, M Bellemare, A Graves, M Riedmiller, A Fidjeland, G Ostrovski","year":"2015","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":51,"raw":"[Mugan and Kuipers, 2012] J. Mugan and B. Kuipers. Au- tonomous learning of high-level states and actions in con- tinuous environments. IEEE Transactions on Autonomous Mental Development, 4(1):70-86, 2012.","title":"Autonomous learning of high-level states and actions in continuous environments","authors":"Kuipers Mugan, ] J Mugan, B Kuipers","year":"2012","venue":"IEEE Transactions on Autonomous Mental Development","doi":null,"url":null,"internal_url":null},{"position":52,"raw":"[Norvig, 1992] P. Norvig. Paradigms of artificial intelli- gence programming: case studies in Common LISP. Mor- gan Kaufmann, 1992.","title":"Paradigms of artificial intelligence programming: case studies in Common LISP","authors":"P Norvig","year":"1992","venue":null,"doi":null,"url":null,"internal_url":null},{"position":53,"raw":"[Palacios and Geffner, 2009] H. Palacios and H. Geffner. Compiling uncertainty away in conformant planning prob- lems with bounded width. JAIR, 35:623-675, 2009.","title":"Compiling uncertainty away in conformant planning problems with bounded width","authors":"H Palacios, H Geffner","year":"2009","venue":"JAIR","doi":null,"url":null,"internal_url":null},{"position":54,"raw":"[Pearl, 1983] J. Pearl. Heuristics. Addison Wesley, 1983.","title":"Heuristics","authors":"J Pearl","year":"1983","venue":null,"doi":null,"url":null,"internal_url":null},{"position":55,"raw":"[Pearl, 1988] J. Pearl. Probabilistic Reasoning in Intelligent Systems. Morgan Kaufmann, 1988.","title":"Probabilistic Reasoning in Intelligent Systems","authors":"J Pearl","year":"1988","venue":null,"doi":null,"url":null,"internal_url":null},{"position":56,"raw":"[Pearl, 2018] J. Pearl. Theoretical impediments to machine learning with seven sparks from the causal revolution. arXiv preprint arXiv:1801.04016, 2018.","title":"Theoretical impediments to machine learning with seven sparks from the causal revolution","authors":"J Pearl","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":57,"raw":"[Ramírez and Geffner, 2010] M. Ramírez and H. Geffner. Probabilistic plan recognition using off-the-shelf classical planners. In Proc. AAAI, 2010.","title":"Probabilistic plan recognition using off-the-shelf classical planners","authors":"M Ramírez, H Geffner","year":"2010","venue":"Proc. AAAI","doi":null,"url":null,"internal_url":null},{"position":58,"raw":"[Rintanen, 2004] J. Rintanen. Complexity of planning with partial observability. In ICAPS, pages 345-354, 2004.","title":"Complexity of planning with partial observability","authors":"J Rintanen","year":"2004","venue":"ICAPS","doi":null,"url":null,"internal_url":null},{"position":59,"raw":"[Rumelhart and McClelland, 1986] D. Rumelhart and J. Mc- Clelland, editors. Parallel distributed processing: explo- rations in the microstructure of cognition. Vol. 1. MIT Press, 1986.","title":"Parallel distributed processing: explorations in the microstructure of cognition","authors":null,"year":"1986","venue":null,"doi":null,"url":null,"internal_url":null},{"position":60,"raw":"[Russell and Norvig, 2009] S. Russell and P. Norvig. Arti- ficial Intelligence: A Modern Approach. Prentice Hall, 2009. 3rd Edition.","title":"Artificial Intelligence: A Modern Approach","authors":"S Russell, P Norvig","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":61,"raw":"[Silver et al., 2017a] D. Silver, T. Hubert, J. Schrittwieser, I. Antonoglou, M. Lai, A. Guez, M. Lanctot, L. Sifre, D. Kumaran, T. Graepel, et al. Mastering chess and shogi by self-play with a general reinforcement learning algo- rithm. arXiv preprint arXiv:1712.01815, 2017.","title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm","authors":"Silver","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":62,"raw":"[Silver et al., 2017b] D. Silver, J. Schrittwieser, K. Si- monyan, I. Antonoglou, A. Huang, A. Guez, T. Hubert, L. Baker, M. Lai, A. Bolton, et al. Mastering the game of go without human knowledge. Nature, 550(7676):354, 2017.","title":"Mastering the game of go without human knowledge","authors":"Silver","year":"2017","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":63,"raw":"[Srivastava et al., 2011] S. Srivastava, N. Immerman, and S. Zilberstein. A new representation and associated al- gorithms for generalized planning. AI, 175(2):615-647, 2011.","title":"A new representation and associated algorithms for generalized planning","authors":"S Srivastava, N Immerman, S Zilberstein","year":"2011","venue":"AI","doi":null,"url":null,"internal_url":null},{"position":64,"raw":"[Stanovich, 2005] K. Stanovich. The robot's rebellion: Find- ing meaning in the age of Darwin. Univ. of Chicago Press, 2005.","title":"The robot's rebellion: Finding meaning in the age of Darwin","authors":"K Stanovich","year":"2005","venue":null,"doi":null,"url":null,"internal_url":null},{"position":65,"raw":"[Sutton and Barto, 1998] R. Sutton and A. Barto. Introduc- tion to Reinforcement Learning. MIT Press, 1998.","title":"Introduction to Reinforcement Learning","authors":"R Sutton, A Barto","year":"1998","venue":null,"doi":null,"url":null,"internal_url":null},{"position":66,"raw":"[Thomas et al., 2017] V. Thomas, J. Pondard, E. Bengio, M. Sarfati, P. Beaudoin, M. Meurs, J. Pineau, D. Precup, and Y. Bengio. Independently controllable features. arXiv preprint, 2017.","title":"Independently controllable features","authors":"V Thomas, J Pondard, E Bengio, M Sarfati, P Beaudoin, M Meurs, J Pineau, D Precup, Y Bengio","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":67,"raw":"[Turing, 1936] A. Turing. On computable numbers, with an application to the Entscheidungsproblem. In Proc. of the London Mathematical Society, volume 42, 1936.","title":"On computable numbers, with an application to the Entscheidungsproblem","authors":"A Turing","year":"1936","venue":"Proc. of the London Mathematical Society","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}