mlsanityData to 14 Oct 2026

Few-Shot Image-to-Semantics Translation for Policy Transfer in Reinforcement Learning

arXiv 2301.13343 ↗First posted 31 Jan 2023cs.LG cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We investigate policy transfer using image-to-semantics translation to mitigate learning difficulties in vision-based robotics control agents. This problem assumes two environments: a simulator environment with semantics, that is, low-dimensional and essential information, as the state space, and a real-world environment with images as the state space. By learning mapping from images to semantics, we can transfer a policy, pre-trained in the simulator, to the real world, thereby eliminating real-world on-policy agent interactions to learn, which are costly and risky. In addition, using image-to-semantics mapping is advantageous in terms of the computational efficiency to train the policy and the interpretability of the obtained policy over other types of sim-to-real transfer strategies. To tackle the main difficulty in learning image-to-semantics mapping, namely the human annotation cost for producing a training dataset, we propose two techniques: pair augmentation with the transition function in the simulator environment and active learning. We observed a reduction in the annotation cost without a decline in the performance of the transfer, and the proposed approach outperformed the existing approach without annotation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 36 references that are in the map. First posted on arXiv 31 Jan 2023.

Builds on

33 of 36 references.

References · 33

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2013Auto-Encoding Variational Bayescited by 4,053
  4. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  5. 2017Adversarial Discriminative Domain Adaptationcited by 1,311
  6. 2018DeepMind Control Suitecited by 956
  7. 2018Recurrent World Models Facilitate Policy Evolutioncited by 785
  8. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 760
  9. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 743
  10. 2016Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collectioncited by 316
  11. 2019Variational Adversarial Active Learningcited by 284
  12. 2017Asymmetric Actor Critic for Image-Based Robot Learningcited by 238
21 more
  1. 2016ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learningcited by 179
  2. 2018Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networkscited by 174
  3. 2018Learning by Playing - Solving Sparse Reward Tasks from Scratchcited by 167
  4. 2017DARLA: Improving Zero-Shot Transfer in Reinforcement Learningcited by 149
  5. 2017Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Graspingcited by 144
  6. 2019Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning?cited by 140
  7. 2018Driving Policy Transfer via Modularity and Abstractioncited by 92
  8. 2020RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Realcited by 91
  9. 2019Diverse mini-batch Active Learningcited by 89
  10. 2020RetinaGAN: An Object-aware Approach to Sim-to-Real Transfercited by 70
  11. 2018Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translationcited by 50
  12. 2020Learning Cross-Domain Correspondence for Control with Dynamics Cycle-Consistencycited by 43
  13. 2018Combined Reinforcement Learning via Abstract Representationscited by 37
  14. 2020Robust Policies via Mid-Level Visual Representations: An Experimental Study in Manipulation and Navigationcited by 32
  15. 2020Robotic Grasping using Deep Reinforcement Learningcited by 28
  16. 2018Active Learning for Regression Using Greedy Samplingcited by 26
  17. 2015Adapting Deep Visuomotor Representations with Weak Pairwise Constraintscited by 25
  18. 2021Policy Transfer across Visual and Dynamics Domain Gaps via Iterative Groundingcited by 12
  19. 2017Adversarial Discriminative Sim-to-real Transfer of Visuo-motor Policiescited by 11
  20. 2016Modular Deep Q Networks for Sim-to-real Transfer of Visuo-motor Policiescited by 5
  21. 2018Towards Governing Agent's Efficacy: Action-Conditional β-VAE for Deep Transparent Reinforcement Learningcited by 1

Built on by

Not cited yet.