论文标题
信息理论任务选择用于元提升学习
Information-theoretic Task Selection for Meta-Reinforcement Learning
论文作者
论文摘要
在元强化学习（META-RL）中，对代理人进行了一组任务培训，以准备并在新的，看不见但相关的任务中更快地学习和学习。培训任务通常是手工制作的，以代表测试任务的预期分布，因此全部用于培训。我们表明，如果适当地选择了培训任务，则鉴于一组培训任务，学习可以更快，更有效（在测试任务中提高性能更好）。我们根据信息理论提出了一种任务选择算法，信息理论任务选择（ITTS），该算法如何优化用于元素元素培训的任务集，而不论它们的生成方式如何。该算法确定了哪些培训任务与测试任务足够相关，并且相互不同。我们从文献中重现了不同的元RL实验，并表明ITT可以改善所有这些实验。
In Meta-Reinforcement Learning (meta-RL) an agent is trained on a set of tasks to prepare for and learn faster in new, unseen, but related tasks. The training tasks are usually hand-crafted to be representative of the expected distribution of test tasks and hence all used in training. We show that given a set of training tasks, learning can be both faster and more effective (leading to better performance in the test tasks), if the training tasks are appropriately selected. We propose a task selection algorithm, Information-Theoretic Task Selection (ITTS), based on information theory, which optimizes the set of tasks used for training in meta-RL, irrespectively of how they are generated. The algorithm establishes which training tasks are both sufficiently relevant for the test tasks, and different enough from one another. We reproduce different meta-RL experiments from the literature and show that ITTS improves the final performance in all of them.
