首页|Patent Issued for Guided uncertainty-aware policy optimization: combining model- free and model-based strategies for sampleefficient learning (USPTO 12109701)
Patent Issued for Guided uncertainty-aware policy optimization: combining model- free and model-based strategies for sampleefficient learning (USPTO 12109701)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
The following quote was obtained by the news editors from the background informa tion supplied by the inventors: “Training robots to accurately perform tasks can use significant memory, time, or computing resources. Sometimes, this can cause training to require extreme amounts of training data, which for some tasks, may be unavailable or prohibitively costly to attain. In some examples, training ma y result in an excessively brittle or unstable system that does not reliably con verge on a solution to a task. Therefore, finding ways to train more effectively and efficiently is an important problem.”
NETL
NSTL
