Corpus ID: 230435929

Context-Aware Safe Reinforcement Learning for Non-Stationary Environments

@article{Chen2021ContextAwareSR,
  title={Context-Aware Safe Reinforcement Learning for Non-Stationary Environments},
  author={B. Chen and Zuxin Liu and Jiacheng Zhu and Mengdi Xu and Wenhao Ding and D. Zhao},
  journal={ArXiv},
  year={2021},
  volume={abs/2101.00531}
}
Safety is a critical concern when deploying reinforcement learning agents for realistic tasks. Recently, safe reinforcement learning algorithms have been developed to optimize the agent’s performance while avoiding violations of safety constraints. However, few studies have addressed the non-stationary disturbances in the environments, which may cause catastrophic outcomes. In this paper, we propose the context-aware safe reinforcement learning (CASRL) method, a meta-learning framework to… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 45 REFERENCES
Safe Reinforcement Learning in Constrained Markov Decision Processes
  • 7
  • PDF
Safe Exploration in Continuous Action Spaces
  • 90
  • PDF
A Lyapunov-based Approach to Safe Reinforcement Learning
  • 122
  • PDF
Learning-Based Model Predictive Control for Safe Exploration
  • 142
  • PDF
Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Method
  • 8
  • PDF
Learning to Adapt in Dynamic, Real-World Environments through Meta-Reinforcement Learning
  • 161
  • Highly Influential
  • PDF
Lyapunov-based Safe Policy Optimization for Continuous Control
  • 45
  • PDF
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
  • 360
  • Highly Influential
  • PDF
Delay-Aware Model-Based Reinforcement Learning for Continuous Control
  • 4
  • PDF
A comprehensive survey on safe reinforcement learning
  • 518
  • PDF
...
1
2
3
4
5
...