arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2103.06398cs.LG
收藏

分析深层策略网络的隐藏激活:为什么表示很重要

Analyzing the Hidden Activations of Deep Policy Networks: Why Representation Matters

Northwestern University(西北大学)

Trevor A. McInroe, Michael Spurrier, Jennifer Sieber, Stephen Conneely

摘要:

我们分析了深度强化学习(RL)代理的神经网络策略的隐藏激活,并根据经验表明,可以先验地知道状态表示是否适合快速学习。高维状态下的RL代理有两个主要的学习负担:(1)学习动作选择策略,(2)学习在给定状态下区分有用和无用的信息。通过使用辅助模型学习这些高维状态的潜在表示,有效地消除了后者的负担,从而加快了训练进度。我们在PyBullet Kuka环境中的任务中研究了这种现象,其中代理必须学会控制机器人抓手来拾取物体。我们的分析揭示了神经网络策略如何在整个训练过程中学习组织其状态空间的内部表示。该分析的结果提供了三个关于RL代理学习深度的主要见解。首先,在政策网络中有一个组织良好的内部代表是学习好的行动选择的先决条件。其次,初始表示不佳可能导致策略网络内不可恢复的崩溃。第三,良好的初始表示允许代理的策略网络甚至在任何训练开始之前组织其内部表示。

英文摘要:

We analyze the hidden activations of neural network policies of deep reinforcement learning (RL) agents and show, empirically, that it's possible to know a priori if a state representation will lend itself to fast learning. RL agents in high-dimensional states have two main learning burdens: (1) to learn an action-selection policy and (2) to learn to discern between useful and non-useful information in a given state. By learning a latent representation of these high-dimensional states with an auxiliary model, the latter burden is effectively removed, thereby leading to accelerated training progress. We examine this phenomenon across tasks in the PyBullet Kuka environment, where an agent must learn to control a robotic gripper to pick up an object. Our analysis reveals how neural network policies learn to organize their internal representation of the state space throughout training. The results from this analysis provide three main insights into how deep RL agents learn. First, a well-organized internal representation within the policy network is a prerequisite to learning good action-selection. Second, a poor initial representation can cause an unrecoverable collapse within a policy network. Third, a good initial representation allows an agent's policy network to organize its internal representation even before any training begins.

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。

↑