Adversarial Intrinsic Motivation for Reinforcement Learning.
作者： Scott Niekum , Peter Stone , Ishan Durugkar , Mauricio Tec
DOI:
关键词: State (computer science) 、 Hindsight bias 、 Reinforcement learning 、 Dual (category theory) 、 Robotics 、 Markov decision process 、 Probability mass function 、 Function (engineering) 、 Artificial intelligence 、 Computer science
摘要: Learning with an objective to minimize the mismatch with a reference distribution has been shown to be useful for generative modeling and imitation learning. In this paper, we …
arxiv.org参考文章(62)
Tom Schaul, Daniel Horgan, David Silver, Karol Gregor, Universal Value Function Approximators international conference on machine learning. pp. 1312- 1320 ,(2015)
Andrew G. Barto, Satinder Singh, Nuttapong Chentanez, Intrinsically Motivated Learning of Hierarchical Collections of Skills ,(2004)
Scott Niekum, Evolved intrinsic reward functions for reinforcement learning national conference on artificial intelligence. pp. 1955- 1956 ,(2010)
M. B. Smyth, Quasi Uniformities: Reconciling Domains with Metric Spaces Proceedings of the 3rd Workshop on Mathematical Foundations of Programming Language Semantics. pp. 236- 253 ,(1987) , 10.1007/3-540-19020-1_12
Andrew Y. Ng, Stuart J. Russell, Daishi Harada, Policy Invariance Under Reward Transformations: Theory and Application to Reward Shaping international conference on machine learning. pp. 278- 287 ,(1999)
Ronald Ortner, Peter Auer, Thomas Jaksch, Near-optimal Regret Bounds for Reinforcement Learning Journal of Machine Learning Research. ,vol. 11, pp. 1563- 1600 ,(2010)
Peter Hart, Nils Nilsson, Bertram Raphael, A Formal Basis for the Heuristic Determination of Minimum Cost Paths IEEE Transactions on Systems Science and Cybernetics. ,vol. 4, pp. 100- 107 ,(1968) , 10.1109/TSSC.1968.300136
Pierre-Yves Oudeyer, Frederic Kaplan, What is Intrinsic Motivation? A Typology of Computational Approaches. Frontiers in Neurorobotics. ,vol. 1, pp. 6- 6 ,(2007) , 10.3389/NEURO.12.006.2007
Gianluca Baldassarre, Tom Stafford, Marco Mirolli, Peter Redgrave, Richard M. Ryan, Andrew Barto, Intrinsic motivations and open-ended development in animals, humans, and robots: an overview. Frontiers in Psychology. ,vol. 5, pp. 985- 985 ,(2014) , 10.3389/FPSYG.2014.00985
Vieri G. Santucci, Gianluca Baldassarre, Marco Mirolli, Which is the best intrinsic motivation signal for learning multiple skills Frontiers in Neurorobotics. ,vol. 7, pp. 22- 22 ,(2013) , 10.3389/FNBOT.2013.00022