论文标题
从次优的演示中判别加权离线模仿学习
Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations
论文作者
论文摘要
我们研究了离线模仿学习（IL）的问题，其中代理商旨在学习最佳的专家行为政策，而无需其他在线环境互动。取而代之的是，该代理来自次优行为的补充离线数据集。解决此问题的先前工作要么要求专家数据占离线数据集的大部分比例，要么需要学习奖励功能并之后执行离线增强学习（RL）。在本文中，我们旨在解决问题，而无需进行奖励学习和离线RL培训的其他步骤，当时示范包含大量次优数据。基于行为克隆（BC），我们引入了一个额外的歧视者，以区分专家和非专家数据。我们提出了一个合作框架，以增强这两个任务的学习，基于此框架，我们设计了一种新的IL算法，其中歧视者的输出是BC损失的权重。实验结果表明，与基线算法相比，我们提出的算法可实现更高的回报和更快的训练速度。
We study the problem of offline Imitation Learning (IL) where an agent aims to learn an optimal expert behavior policy without additional online environment interactions. Instead, the agent is provided with a supplementary offline dataset from suboptimal behaviors. Prior works that address this problem either require that expert data occupies the majority proportion of the offline dataset, or need to learn a reward function and perform offline reinforcement learning (RL) afterwards. In this paper, we aim to address the problem without additional steps of reward learning and offline RL training for the case when demonstrations contain a large proportion of suboptimal data. Built upon behavioral cloning (BC), we introduce an additional discriminator to distinguish expert and non-expert data. We propose a cooperation framework to boost the learning of both tasks, Based on this framework, we design a new IL algorithm, where the outputs of discriminator serve as the weights of the BC loss. Experimental results show that our proposed algorithm achieves higher returns and faster training speed compared to baseline algorithms.
