{"type":"ScholarlyArticle","title":"Can Meta-Interpretive Learning outperform Deep Reinforcement Learning of Evaluable Game strategies?","authors":[{"name":"Céline Hocquette","slug":"celine-hocquette","given":"Céline","family":"Hocquette","affiliation":"Imperial College London , Department of Computing"}],"abstract":"World-class human players have been outperformed in a number of complex two person games such as Go by Deep Reinforcement Learning systems GO. However, several drawbacks can be identified for these systems: 1) The data efficiency is unclear given they appear to require far more training games to achieve such performance than any human player might experience in a lifetime. 2) These systems are not easily interpretable as they provide limited explanation about how decisions are made. 3) These systems do not provide transferability of the learned strategies to other games. We study in this work how an explicit logical representation can overcome these limitations and introduce a new logical system called MIGO designed for learning two player game optimal strategies. It benefits from a strong inductive bias which provides the capability to learn efficiently from a few examples of games played. Additionally, MIGO's learned rules are relatively easy to comprehend, and are demonstrated to achieve significant transfer learning.","doi":"10.24963/ijcai.2019/909","url":"https://ijcai.org/proceedings/2019/909","pdf":"https://ijcai.org/proceedings/2019/0909.pdf","markdown":"https://ijcai.org/proceedings/2019/909.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/909","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Doctoral Consortium","track":"Doctoral Consortium","number":909,"pages":{"first":6440,"last":6441},"keywords":["Machine Learning: Relational Learning","Heuristic Search and Game Playing: Game Playing and Machine Learning"],"videos":[],"references":[{"position":1,"raw":"[Džeroski et al., 2001] Sašo Džeroski, Luc De Raedt, and Kurt Driessens. Relational reinforcement learning. Ma- chine Learning, 43(1):7-52, Apr 2001.","title":"Relational reinforcement learning","authors":"Sašo Džeroski, Luc De Raedt, Kurt Driessens","year":"2001","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Lin et al., 2014] Dianhuan Lin, Eyal Dechter, and Kevin M. et al Ellis. Bias reformulation for one-shot function in- duction. In In Proceedings of the 23rd European Confer- ence on Artificial Intelligence (ECAI 2014), pages 525- 530,. IOS Press, 2014.","title":"Bias reformulation for one-shot function induction","authors":"Lin","year":"2014","venue":"Proceedings of the 23rd European Conference on Artificial Intelligence (ECAI 2014)","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Michie, 1963] Donald Michie. Experiments on the mech- anization of game-learning part i. characterization of the model and its parameters. The Computer Journal, Volume 6, Issue 3, pages 232-236, 1963.","title":"Experiments on the mechanization of game-learning part i. characterization of the model and its parameters","authors":"Donald Michie","year":"1963","venue":"The Computer Journal","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Mnih et al., 2015] Volodymyr Mnih, Koray Kavukcuoglu, David Silver, and et al. Human-level control through deep reinforcement learning. Nature, 518:529-533, 02 2015.","title":"Human-level control through deep reinforcement learning","authors":"Mnih","year":"2015","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Muggleton et al., 2014] Stephen H. Muggleton, Dianhuan Lin, Niels Pahlavi, and Alireza Tamaddoni-Nezhad. Meta- interpretive learning: application to grammatical infer- ence. Machine Learning 94, pages 25-49, 2014.","title":"Metainterpretive learning: application to grammatical inference","authors":"H Stephen, Dianhuan Muggleton, Niels Lin, Alireza Pahlavi, Tamaddoni-Nezhad","year":"2014","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Muggleton et al., 2015] Stephen H. Muggleton, Dianhuan Lin, and Alireza Tamaddoni-Nezhad. Meta-interpretive learning of higher-order dyadic datalog: predicate inven- tion revisited. Machine Learning, 100(1):49-73, Jul 2015.","title":"Meta-interpretive learning of higher-order dyadic datalog: predicate invention revisited","authors":"H Stephen, Dianhuan Muggleton, Alireza Lin, Tamaddoni-Nezhad","year":"2015","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Quinlan, 1983] J. Ross Quinlan. Learning Efficient Classi- fication Procedures and Their Application to Chess End Games, pages 463-482. Springer Berlin Heidelberg, Berlin, Heidelberg, 1983.","title":"Learning Efficient Classification Procedures and Their Application to Chess End Games","authors":"J, Ross Quinlan","year":"1983","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Shapiro and Niblett, 1982] Alen Shapiro and Timothy Niblett. Automatic induction of classification rules for a chess endgame. In M.R.B. Clarke, editor, Advances in Computer Chess, volume 3, pages 73-91. Pergammon, Oxford, 1982.","title":"Automatic induction of classification rules for a chess endgame","authors":"Alen Shapiro, Timothy Niblett","year":"1982","venue":"Advances in Computer Chess","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Silver et al., 2016] David Silver, Aja Huang, Chris J. Mad- dison, Arthur Guez, and et al. Mastering the game of go with deep neural networks and tree search. 529:484-489, 01 2016.","title":"Mastering the game of go with deep neural networks and tree search","authors":"David Silver, Aja Huang, Chris J Maddison, Arthur Guez","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Watkins, 1989] Christopher Watkins. Learning from de- layed rewards, phd thesis. 1989.","title":"Learning from delayed rewards","authors":"Christopher Watkins","year":"1989","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}