Proposed Architectural and Representational Modifications
semanticscholar(2021)
摘要
The BabyAI platform is designed to measure the sample efficiency of training an agent to follow groundedlanguage instructions. BabyAI 1.0 presents baseline results of an agent trained by deep imitation or reinforcement learning. BabyAI 1.1 improves the agent’s architecture in three minor ways. This increases reinforcement learning sample efficiency by up to 3× and improves imitation learning performance on the hardest level from 77% to 90.4%. We hope that these improvements increase the computational efficiency of BabyAI experiments and help users design better agents.
更多查看译文
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