Goal-Aware Cross-Entropy for Multi-Target Reinforcement LearningDownload PDF

21 May 2021, 20:44 (edited 24 Jan 2022)NeurIPS 2021 PosterReaders: Everyone
  • Keywords: goal-aware, attention, reinforcement learning, multi-target environment, visual navigation, manipulation
  • TL;DR: We propose goal-aware cross-entropy loss and attention networks in multi-target environments.
  • Abstract: Learning in a multi-target environment without prior knowledge about the targets requires a large amount of samples and makes generalization difficult. To solve this problem, it is important to be able to discriminate targets through semantic understanding. In this paper, we propose goal-aware cross-entropy (GACE) loss, that can be utilized in a self-supervised way using auto-labeled goal states alongside reinforcement learning. Based on the loss, we then devise goal-discriminative attention networks (GDAN) which utilize the goal-relevant information to focus on the given instruction. We evaluate the proposed methods on visual navigation and robot arm manipulation tasks with multi-target environments and show that GDAN outperforms the state-of-the-art methods in terms of task success ratio, sample efficiency, and generalization. Additionally, qualitative analyses demonstrate that our proposed method can help the agent become aware of and focus on the given instruction clearly, promoting goal-directed behavior.
  • Supplementary Material: pdf
  • Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.
  • Code: https://github.com/kibeomKim/GACE-GDAN
15 Replies