mlsanityData to 7 Oct 2026

Learning to View: Decision Transformers for Active Object Detection

arXiv 2301.09544 ↗First posted 23 Jan 2023cs.RO cs.CVcited by 10

On the map: Offline RL and imitation learning from data → Language-conditioned policies and VLAs

Abstract (arXiv)

Active perception describes a broad class of techniques that couple planning and perception systems to move the robot in a way to give the robot more information about the environment. In most robotic systems, perception is typically independent of motion planning. For example, traditional object detection is passive: it operates only on the images it receives. However, we have a chance to improve the results if we allow planning to consume detection signals and move the robot to collect views that maximize the quality of the results. In this paper, we use reinforcement learning (RL) methods to control the robot in order to obtain images that maximize the detection quality. Specifically, we propose using a Decision Transformer with online fine-tuning, which first optimizes the policy with a pre-collected expert dataset and then improves the learned policy by exploring better solutions in the environment. We evaluate the performance of proposed method on an interactive dataset collected from an indoor scenario simulator. Experimental results demonstrate that our method outperforms all baselines, including expert policy and pure offline RL methods. We also provide exhaustive analyses of the reward distribution and observation space.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Placed in Language-conditioned policies and VLAs, one of 13 directions in Offline RL and imitation learning from data. Builds on 26 of its 37 references that are in the map. First posted on arXiv 23 Jan 2023.

Builds on

26 of 37 references.

References · 26

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2020End-to-End Object Detection with Transformerscited by 7,384
  4. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  5. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,873
  6. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,777
  7. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
  8. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,406
  9. 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 1,245
  10. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,179
  11. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  12. 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 850
14 more
  1. 2020AWAC: Accelerating Online Reinforcement Learning with Offline Datasetscited by 647
  2. 2021Offline Reinforcement Learning as One Big Sequence Modeling Problemcited by 636
  3. 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 256
  4. 2022A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problemscited by 228
  5. 2022Online Decision Transformercited by 194
  6. 2021Generalized Decision Transformer for Offline Hindsight Information Matchingcited by 105
  7. 2022Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learningcited by 93
  8. 2018Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learningcited by 91
  9. 2020Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Methodcited by 74
  10. 2022You Can't Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environmentscited by 62
  11. 2017A Dataset for Developing and Benchmarking Active Visioncited by 50
  12. 2022Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoningcited by 33
  13. 2022Interactron: Embodied Adaptive Object Detectioncited by 21
  14. 2021Transfer learning with causal counterfactual reasoning in Decision Transformerscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 1; 2025: 0; 2026: 4.

10 papers.

  1. 2023Evidential Active Recognition: Intelligent and Prudent Open-World Embodied Perceptioncited by 15
  2. 2023Active Open-Vocabulary Recognition: Let Intelligent Moving Mitigate CLIP Limitationscited by 6
  3. 2023Privacy Risks in Reinforcement Learning for Household Robotscited by 4
  4. 2023Interactive Semantic Map Representation for Skill-based Visual Object Navigationcited by 2
  5. 2023SegmATRon: Embodied Adaptive Semantic Segmentation for Indoor Environmentcited by 1
  6. 2024Decision Transformer for Enhancing Neural Local Search on the Job Shop Scheduling Problemcited by 1
  7. 2026Does YOLO Really Need to See Every Training Image in Every Epoch?cited by 1
  8. 2026Toward Active Object Detection for UAVs in the Wild: A Large-Scale Dataset, Benchmark and Methodcited by 1
  9. 2026See, Act, Adapt: Active Perception for Unsupervised Cross-Domain Visual Adaptation via Personalized VLM-Guided Agentcited by 0
  10. 2026GoStop: Reinforcement Learning for Adaptive Temporal Aggregation in Event-Based Feature Trackingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning
  2. 2025AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention
  3. 2022How to Spend Your Robot Time: Bridging Kickstarting and Offline Reinforcement Learning for Vision-based Robotic Manipulation
  4. 2025Robust Object Detection for Autonomous Driving via Curriculum-Guided Group Relative Policy Optimization
  5. 2025Reinforcement Learning for Large Model: A Survey
  6. 2025RLGF: Reinforcement Learning with Geometric Feedback for Autonomous Driving Video Generation
  7. 2022Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information
  8. 2024Optimizing Active Perception for Learning Simultaneous Viewpoint Selection and Manipulation with Diffusion Policy