Safe Reinforcement Learning With Model Uncertainty Estimates

@article{Ltjens2019SafeRL,
  title={Safe Reinforcement Learning With Model Uncertainty Estimates},
  author={Bj{\"o}rn L{\"u}tjens and Michael Everett and J. How},
  journal={2019 International Conference on Robotics and Automation (ICRA)},
  year={2019},
  pages={8662-8668}
}
Many current autonomous systems are being designed with a strong reliance on black box predictions from deep neural networks (DNNs). However, DNNs tend to be overconfident in predictions on unseen data and can give unpredictable results for far-from-distribution test data. The importance of predictions that are robust to this distributional shift is evident for safety-critical applications, such as collision avoidance around pedestrians. Measures of model uncertainty can be used to identify… Expand
37 Citations
Fully Bayesian Recurrent Neural Networks for Safe Reinforcement Learning
  • 1
  • Highly Influenced
  • PDF
Learning Resilient Behaviors for Navigation Under Uncertainty Environments
  • 2
  • PDF
Learning Resilient Behaviors for Navigation Under Uncertainty
  • 2
Multiplicative Controller Fusion: Leveraging Algorithmic Priors for Sample-efficient Reinforcement Learning and Safe Sim-To-Real Transfer
  • PDF
Deep Reactive Planning in Dynamic Environments
  • 1
  • PDF
Residual Reactive Navigation: Combining Classical and Learned Navigation Strategies For Deployment in Unknown Environments
  • 6
  • PDF
Certified Adversarial Robustness for Deep Reinforcement Learning
  • 12
  • PDF
...
1
2
3
4
...

References

SHOWING 1-10 OF 50 REFERENCES
Safe Visual Navigation via Deep Learning and Novelty Detection
  • 105
  • PDF
Uncertainty-Aware Reinforcement Learning for Collision Avoidance
  • 158
  • Highly Influential
  • PDF
Socially aware motion planning with deep reinforcement learning
  • 257
  • PDF
Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning
  • Michael Everett, Y. Chen, J. How
  • Computer Science, Engineering
  • 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2018
  • 150
  • PDF
Risk-Sensitive Reinforcement Learning
  • 112
  • PDF
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
  • 2,841
  • Highly Influential
  • PDF
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
  • 1,239
  • PDF
Risk-Sensitive Reinforcement Learning
  • 139
  • PDF
...
1
2
3
4
5
...