A Multi-Objective Approach to Mitigate Negative Side Effects
作者： Sandhya Saisubramanian , Ece Kamar , Shlomo Zilberstein
关键词:
摘要: … Agents operating in unstructured environments often create negative side effects (NSE) that may not be easy to identify at design time. We examine how various forms of human …
ijcai.org
sci-hub.st 参考文章(7)
Shlomo Zilberstein, Sven Seuken, Improved memory-bounded dynamic programming for decentralized POMDPs uncertainty in artificial intelligence. pp. 344- 351 ,(2007)
D. M. Roijers, P. Vamplew, S. Whiteson, R. Dazeley, A survey of multi-objective sequential decision-making Journal of Artificial Intelligence Research. ,vol. 48, pp. 67- 113 ,(2013) , 10.1613/JAIR.3987
Dylan Hadfield-Menell, Pieter Abbeel, Anca Dragan, Stuart Russell, Smitha Milli, Inverse Reward Design arXiv: Artificial Intelligence. ,(2017)
Shun Zhang, Edmund H. Durfee, Satinder Singh, Minimax-Regret Querying on Side Effects for Safe Optimality in Factored Markov Decision Processes Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. pp. 4867- 4873 ,(2018) , 10.24963/IJCAI.2018/676
Shlomo Zilberstein, Luis Pineda, Kyle Hollins Wray, Sandhya Saisubramanian, Planning in Stochastic Environments with Goal Uncertainty arXiv: Artificial Intelligence. ,(2018)
Ramya Ramakrishnan, Ece Kamar, Besmira Nushi, Debadeepta Dey, Julie Shah, Eric Horvitz, Overcoming Blind Spots in the Real World: Leveraging Complementary Abilities for Joint Execution. national conference on artificial intelligence. ,vol. 33, pp. 6137- 6145 ,(2019) , 10.1609/AAAI.V33I01.33016137
Shane Legg, Miljan Martic, Victoria Krakovna, Laurent Orseau, Ramana Kumar, Penalizing side effects using stepwise relative reachability arXiv: Learning. ,(2018)