Assured Learning-enabled Autonomy: A Metacognitive Reinforcement Learning Framework

TL;DR

This paper introduces a metacognitive reinforcement learning framework that adaptively adjusts reward functions to ensure safety and performance guarantees in autonomous systems, using Bayesian RL for proactive safety management.

Contribution

It presents a novel hierarchical RL approach with a metacognitive layer that monitors safety and adapts reward parameters to ensure constraint satisfaction.

Findings

The framework guarantees safety constraints in autonomous control.

The metacognitive layer effectively prevents safety violations.

Simulation results validate the approach's effectiveness.

Abstract

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 paper 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.