François Chollet@fchollet · XAI 摘要
大多数人类任务并非马尔可夫过程，最优的下一步行动无法仅凭当前状态决定。它很大程度上取决于过去的轨迹、原始意图和上下文约束。一个无法以绝对保真度压缩和追踪其过去轨迹的智能体，其效用可能只有能做到这一点的智能体的20%。
Most human tasks are not Markovian， the optimal next action cannot be determined solely by looking at the current state. It depends heavily on the past trajectory， the original intent， and context constraints. An agent that cannot compress and track its past trajectory with absolute fidelity is maybe 20% as useful as one that can.