mlsanityData to 7 Oct 2026

Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning

arXiv 2110.12985 ↗First posted 25 Oct 2021cs.LG cs.AI cs.ROcited by 7

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 36 of its 50 references that are in the map. First posted on arXiv 25 Oct 2021.

Builds on

36 of 50 references.

References · 36

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  5. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  6. 2018World Modelscited by 1,444
  7. 2017Hindsight Experience Replaycited by 1,096
  8. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,013
  9. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 773
  10. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
  11. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 730
  12. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 685
24 more
  1. 2020Reinforcement Learning with Augmented Datacited by 452
  2. 2016Reinforcement Learning with Unsupervised Auxiliary Taskscited by 400
  3. 2016Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learningcited by 351
  4. 2019Improving Sample Efficiency in Model-Free Reinforcement Learning from Imagescited by 268
  5. 2018Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Researchcited by 256
  6. 2017Automatic Goal Generation for Reinforcement Learning Agentscited by 252
  7. 2018Visual Reinforcement Learning with Imagined Goalscited by 248
  8. 2016ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learningcited by 178
  9. 2017Visualizing and Understanding Atari Agentscited by 141
  10. 2018Building Generalizable Agents with a Realistic and Rich 3D Environmentcited by 109
  11. 2018Visual Representations for Semantic Target Driven Navigationcited by 89
  12. 2019Towards Interpretable Reinforcement Learning Using Attention Augmented Agentscited by 82
  13. 2018Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Costcited by 79
  14. 2018CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learningcited by 78
  15. 2016Loss is its own Reward: Self-Supervision for Reinforcement Learningcited by 72
  16. 2017Gated-Attention Architectures for Task-Oriented Language Groundingcited by 72
  17. 2020Goal-Aware Prediction: Learning to Model What Matterscited by 45
  18. 2019Maximum Entropy-Regularized Multi-Goal Reinforcement Learningcited by 39
  19. 2019Situational Fusion of Visual Representation for Visual Navigationcited by 28
  20. 2018Reinforcement Learning of Active Vision for Manipulating Objects under Occlusionscited by 25
  21. 2017Multi-focus Attention Network for Efficient Deep Reinforcement Learningcited by 10
  22. 2019An Actor-Critic-Attention Mechanism for Deep Reinforcement Learning in Multi-view Environmentscited by 5
  23. 2018GAPLE: Generalizable Approaching Policy LEarning for Robotic Object Searching in Indoor Environmentcited by 3
  24. 2018Scaling All-Goals Updates in Reinforcement Learning Using Convolutional Neural Networkscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 1; 2025: 1; 2026: 1.

7 papers.

  1. 2023RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalizationcited by 27
  2. 2022Unsupervised Representation Learning in Deep Reinforcement Learning: A Reviewcited by 18
  3. 2026Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systemscited by 16
  4. 2023Visual Hindsight Self-Imitation Learning for Interactive Navigationcited by 5
  5. 2023L-SA: Learning Under-Explored Targets in Multi-Target Reinforcement Learningcited by 2
  6. 2024Unveiling the Significance of Toddler-Inspired Reward Transition in Goal-Oriented Reinforcement Learningcited by 2
  7. 2025From Sparse to Dense: Toddler-inspired Reward Transition in Goal-Oriented Reinforcement Learningcited by 2