Explainable Reinforcement Learning via Reward Decomposition
暂无分享,去创建一个
Alan Fern | Finale Doshi-Velez | M. Erwig | Zoe Juozapaitis | Anurag Koul | Martin Erwig | F. Doshi-Velez
[1] Michael I. Jordan,et al. MASSACHUSETTS INSTITUTE OF TECHNOLOGY ARTIFICIAL INTELLIGENCE LABORATORY and CENTER FOR BIOLOGICAL AND COMPUTATIONAL LEARNING DEPARTMENT OF BRAIN AND COGNITIVE SCIENCES , 1996 .
[2] Jonas Karlsson. Task Decomposition in Reinforcement Learning , 1994 .
[3] Richard W. Prager,et al. A Modular Q-Learning Architecture for Manipulator Task Decomposition , 1994, ICML.
[4] Mahesan Niranjan,et al. On-line Q-learning using connectionist systems , 1994 .
[5] Thomas G. Dietterich. Hierarchical Reinforcement Learning with the MAXQ Value Function Decomposition , 1999, J. Artif. Intell. Res..
[6] Stuart J. Russell,et al. Q-Decomposition for Reinforcement Learning Agents , 2003, ICML.
[7] Nikos A. Vlassis,et al. Sparse cooperative Q-learning , 2004, ICML.
[8] Pascal Poupart,et al. Minimal Sufficient Explanations for Factored Markov Decision Processes , 2009, ICAPS.
[9] Jimmy Ba,et al. Adam: A Method for Stochastic Optimization , 2014, ICLR.
[10] Shane Legg,et al. Human-level control through deep reinforcement learning , 2015, Nature.
[11] Romain Laroche,et al. Hybrid Reward Architecture for Reinforcement Learning , 2017, NIPS.
[12] Sheila A. McIlraith,et al. Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning , 2018, ICML.
[13] Richard Socher,et al. Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learning , 2017, ICLR.