arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1612.08810cs.LGcs.AIcs.NE
收藏

The Predictron:端到端学习和规划

The Predictron: End-To-End Learning and Planning

DeepMind

David Silver, Hado van Hasselt, Matteo Hessel, Tom Schaul, Arthur Guez, Tim Harley, Gabriel Dulac-Arnold, David Reichert, Neil Rabinowitz, Andre Barreto, Thomas Degris

摘要:

人工智能的关键挑战之一是学习在规划背景下有效的模型。在本文档中,我们介绍了predictron架构。预测器由一个完全抽象的模型组成,由马尔可夫奖励过程表示,可以向前滚动多个“想象”的规划步骤。Predictron的每次向前传递都会在多个规划深度上积累内部奖励和价值。预测器被端到端地训练,以便使这些累积值精确地近似真实的价值函数。我们应用predictron程序生成的随机迷宫和模拟器的游戏池。预测器产生的预测比传统的深度神经网络架构要准确得多。

英文摘要:

One of the key challenges of artificial intelligence is to learn models that are effective in the context of planning. In this document we introduce the predictron architecture. The predictron consists of a fully abstract model, represented by a Markov reward process, that can be rolled forward multiple "imagined" planning steps. Each forward pass of the predictron accumulates internal rewards and values over multiple planning depths. The predictron is trained end-to-end so as to make these accumulated values accurately approximate the true value function. We applied the predictron to procedurally generated random mazes and a simulator for the game of pool. The predictron yielded significantly more accurate predictions than conventional deep neural network architectures.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑