制約を報酬として:報酬関数なしでロボットを強化学習する手法
Constraints as Rewards: Reinforcement Learning for Robots without Reward Functions
報酬関数の設計を不要にするため、複数の制約関数でタスクを定式化し、ラグランジュ法で制約付き強化学習を解く「Constraints as Rewards」を提案し、六輪伸縮脚ロボットの起立動作生成で有効性を示した。
著者: Yu Ishihara, Noriaki Takasugi, Kotaro Kawakami, Masaya Kinoshita, Kazumi Aoyama
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
Reinforcement learning has become an essential algorithm for generating complex robotic behaviors. However, to learn such behaviors, it is necessary to design a reward function that describes the task, which often consists of multiple objectives that needs to be balanced. This tuning process is known as reward engineering and typically involves extensive trial-and-error. In this paper, to avoid this trial-and-error process, we propose the concept of Constraints as Rewards (CaR). CaR formulates the task objective using multiple constraint functions instead of a reward function and solves a reinforcement learning problem with constraints using the Lagrangian-method. By adopting this approach, different objectives are automatically balanced, because Lagrange multipliers serves as the weights among the objectives. In addition, we will demonstrate that constraints, expressed as inequalities, provide an intuitive interpretation of the optimization target designed for the task. We apply the proposed method to the standing-up motion generation task of a six-wheeled-telescopic-legged robot and demonstrate that the proposed method successfully acquires the target behavior, even though it is challenging to learn with manually designed reward functions.
