.png){kind=icon}
返回
Assured learning-enabled autonomy: A metacognitive reinforcement learning framework
.png){kind=icon}
OA
AI
DOI：10.1002/acs.3326.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Reinforcement learning (RL) agents with pre-specified reward functions cannot provide guaranteed safety across variety of circumstances that an uncertain system might encounter. To guarantee performance while assuring satisfaction of safety constraints across variety of circumstances, an assured autonomous control framework is presented in this article by empowering RL algorithms with metacognitive learning capabilities. More specifically, adapting the reward function parameters of the RL agent is performed in a metacognitive decision-making layer to assure the feasibility of RL agent. That is, to assure that the learned policy by the RL agent satisfies safety constraints specified by signal temporal logic while achieving as much performance as possible. The metacognitive layer monitors any possible future safety violation under the actions of the RL agent and employs a higher-layer Bayesian RL algorithm to proactively adapt the reward function for the lower-layer RL agent. To minimize the higher-layer Bayesian RL intervention, a fitness function is leveraged by the metacognitive layer as a metric to evaluate success of the lower-layer RL agent in satisfaction of safety and liveness specifications, and the higher-layer Bayesian RL intervenes only if there is a risk of lower-layer RL failure. Finally, a simulation example is provided to validate the effectiveness of the proposed approach.
Keyword:
assured autonomy
Bayesian optimization
learning-enabled control
optimal control
reinforcement learning
期刊
IF:
3.8
论文数:
2.6K
被引数:
3.6K
机构
引用论文
.png){kind=icon}
分享收藏Autophagy inhibition contributes to radiation sensitization of esophageal squamous carcinoma cells
PREAI
分享收藏分享收藏
Adaptive predictive control of a differential drive robot tuned with reinforcement learning具有强化学习的差分驱动机器人的自适应预测控制
PREAI
分享收藏
查看更多内容