Transfer in reinforcement learning (RL) refers to the idea of applying
knowledge gained from previous tasks to solving related tasks. Learning a
universal value function (Schaul et al., 2015), which generalizes over goals
and states, has previously been shown to be useful for transfer.
我们提出了一种基于 successor features 和 generalized policy improvement 的转移框架，用于处理奖励函数在不同任务之间变化的情况，并且可以在不同任务之间自由地交换信息，同时具有转移策略的性能保证。在导航任务和控制模拟机械臂中，该方法成功地促进了优化的转移，明显优于其他方法.