Demonstration-Efficient Inverse Reinforcement Learning in Procedurally Generated Environments
2021 IEEE Conference on Games (CoG)(2021)
摘要
Deep Reinforcement Learning achieves very good results in domains where reward functions can be manually engineered. At the same time, there is growing interest within the community in using games based on Procedurally Content Generation (PCG) as benchmark environments since this type of environment is perfect for studying overfitting and generalization of agents under domain shift. Inverse Reinfo...
更多查看译文
关键词
Training,Atmospheric modeling,Conferences,Reinforcement learning,Games,Benchmark testing,Task analysis
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要