论文信息 - MORL-Glue: a benchmark suite for multi-objective reinforcement learning - 字舞流文

MORL-Glue: a benchmark suite for multi-objective reinforcement learning

Peter Vamplew | Evan Dekker | Diederik M. Roijers | Richard Dazeley | Dean Webb | Luisa M Zintgraf | Rustam Issabekov

[1] Csaba Szepesvári,et al. Multi-criteria Reinforcement Learning , 1998, ICML.

[2] Shimon Whiteson. Why Multi-objective Reinforcement Learning? , 2015 .

[3] Shimon Whiteson,et al. A Survey of Multi-Objective Sequential Decision-Making , 2013, J. Artif. Intell. Res..

[4] Shimon Whiteson,et al. Generalized Domains for Empirical Evaluations in Reinforcement Learning , 2009 .

[5] Brian Tanner,et al. RL-Glue: Language-Independent Software for Reinforcement-Learning Experiments , 2009, J. Mach. Learn. Res..

[6] Frans A. Oliehoek,et al. Quality Assessment of MORL Algorithms: A Utility-Based Approach , 2015 .

[7] Evan Dekker,et al. Empirical evaluation methods for multiobjective reinforcement learning algorithms , 2011, Machine Learning.