DEAR：无需重建的强化学习解耦环境与智能体表征
DEAR: Disentangled Environment and Agent Representations for Reinforcement Learning without Reconstruction
AI总结：
本文提出DEAR方法，利用智能体分割掩码作为监督学习环境与智能体的解耦表征，无需重建视觉观测，并将其作为辅助损失提升视觉强化学习的样本效率，在Distracting DeepMind control suite和Franka Kitchen任务上以更少参数超越现有方法。
摘要：
强化学习（RL）算法可以从视觉观测中学习机器人控制任务，但它们通常需要大量数据，尤其是当视觉场景复杂且非结构化时。在本文中，我们探索智能体对其自身形状的知识如何提高视觉RL方法的样本效率。我们提出一种新方法，即解耦环境与智能体表征（DEAR），该方法使用智能体的分割掩码作为监督，通过特征分离约束学习环境和智能体的解耦表征。与先前方法不同，DEAR不需要重建视觉观测。这些表征随后被用作RL目标的辅助损失，鼓励智能体关注环境中相关的特征。我们在两个具有挑战性的基准上评估DEAR：Distracting DeepMind control suite和Franka Kitchen操作任务。我们的发现表明，DEAR在样本效率上超越了最先进的方法，在参数减少的情况下实现了相当或更优的性能。我们的结果表明，将智能体知识整合到视觉RL方法中有可能提升其学习效率和鲁棒性。
英文摘要：
Reinforcement Learning (RL) algorithms can learn robotic control tasks from visual observations, but they often require a large amount of data, especially when the visual scene is complex and unstructured. In this paper, we explore how the agent's knowledge of its shape can improve the sample efficiency of visual RL methods. We propose a novel method, Disentangled Environment and Agent Representations (DEAR), that uses the segmentation mask of the agent as supervision to learn disentangled representations of the environment and the agent through feature separation constraints. Unlike previous approaches, DEAR does not require reconstruction of visual observations. These representations are then used as an auxiliary loss to the RL objective, encouraging the agent to focus on the relevant features of the environment. We evaluate DEAR on two challenging benchmarks: Distracting DeepMind control suite and Franka Kitchen manipulation tasks. Our findings demonstrate that DEAR surpasses state-of-the-art methods in sample efficiency, achieving comparable or superior performance with reduced parameters. Our results indicate that integrating agent knowledge into visual RL methods has the potential to enhance their learning efficiency and robustness.
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。
