ファジィ論理に基づく適応的報酬整形によるロバスト強化学習
Fuzzy Logic Theory-based Adaptive Reward Shaping for Robust Reinforcement Learning (FARS)
ファジィ論理を用いて人間の知識を報酬設計に組み込み、状態に応じて報酬を適応的に調整する手法を提案。ドローン競技タスクで収束の高速化と性能ばらつきの低減を実証した。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Hürkan Şahin, Van Huyen Dang, Erdi Sayar, Alper Yegenoglu, Erdal Kayacan
分類: cs.RO
原文アブストラクト
Reinforcement learning (RL) often struggles in real-world tasks with high-dimensional state spaces and long horizons, where sparse or fixed rewards severely slow down exploration and cause agents to get trapped in local optima. This paper presents a fuzzy logic based reward shaping method that integrates human intuition into RL reward design. By encoding expert knowledge into adaptive and interpreable terms, fuzzy rules promote stable learning and reduce sensitivity to hyperparameters. The proposed method leverages these properties to adapt reward contributions based on the agent state, enabling smoother transitions between fast motion and precise control in challenging navigation tasks. Extensive simulation results on autonomous drone racing benchmarks show stable learning behavior and consistent task performance across scenarios of increasing difficulty. The proposed method achieves faster convergence and reduced performance variability across training seeds in more challenging environments, with success rates improving by up to approximately 5 percent compared to non fuzzy reward formulations.
関連論文
- 計画に基づく緩和型報酬整形による目標指向タスクの学習効率化強化学習/報酬整形
