Target-driven visual navigation in indoor scenes using deep reinforcement learning

@article{Zhu2017TargetdrivenVN,
  title={Target-driven visual navigation in indoor scenes using deep reinforcement learning},
  author={Yuke Zhu and R. Mottaghi and Eric Kolve and Joseph J. Lim and A. Gupta and Li Fei-Fei and A. Farhadi},
  journal={2017 IEEE International Conference on Robotics and Automation (ICRA)},
  year={2017},
  pages={3357-3364}
}
Two less addressed issues of deep reinforcement learning are (1) lack of generalization capability to new goals, and (2) data inefficiency, i.e., the model requires several (and often costly) episodes of trial and error to converge, which makes it impractical to be applied to real-world scenarios. In this paper, we address these two issues and apply our model to target-driven visual navigation. To address the first issue, we propose an actor-critic model whose policy is a function of the goal… Expand
Vision-based Navigation Using Deep Reinforcement Learning
Effective Deep Reinforcement Learning Setups for Multiple Goals on Visual Navigation
Visual Navigation in Real-World Indoor Environments Using End-to-End Deep Reinforcement Learning
Target-driven indoor visual navigation using inverse reinforcement learning
A deep Q network for robotic planning from image
A Few Shot Adaptation of Visual Navigation Skills to New Observations using Meta-Learning
Target-Driven Navigation with Imitation Learning
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 56 REFERENCES
End-to-End Training of Deep Visuomotor Policies
ViZDoom: A Doom-based AI research platform for visual reinforcement learning
Policy Distillation
Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning
High speed obstacle avoidance using monocular vision and reinforcement learning
View-based Maps
VirtualWorlds as Proxy for Multi-object Tracking Analysis
Trajectory Optimization using Reinforcement Learning for Map Exploration
...
1
2
3
4
5
...