Safe Exploration of State and Action Spaces in Reinforcement Learning
It addresses the challenge of minimizing damage during exploration in high-dimensional state-action spaces for applications such as robotics and autonomous systems, representing an incremental improvement over traditional unsafe methods.
The paper tackles the problem of safe exploration in reinforcement learning for dangerous tasks by introducing the PI-SRL algorithm, which safely improves suboptimal behaviors and efficiently learns from environment experience, evaluated in tasks like automatic car parking and helicopter hovering.
In this paper, we consider the important problem of safe exploration in reinforcement learning. While reinforcement learning is well-suited to domains with complex transition dynamics and high-dimensional state-action spaces, an additional challenge is posed by the need for safe and efficient exploration. Traditional exploration techniques are not particularly useful for solving dangerous tasks, where the trial and error process may lead to the selection of actions whose execution in some states may result in damage to the learning system (or any other system). Consequently, when an agent begins an interaction with a dangerous and high-dimensional state-action space, an important question arises; namely, that of how to avoid (or at least minimize) damage caused by the exploration of the state-action space. We introduce the PI-SRL algorithm which safely improves suboptimal albeit robust behaviors for continuous state and action control tasks and which efficiently learns from the experience gained from the environment. We evaluate the proposed method in four complex tasks: automatic car parking, pole-balancing, helicopter hovering, and business management.