Enhanced-FQL($λ$), an Efficient and Interpretable RL with novel Fuzzy Eligibility Traces and Segmented Experience Replay
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915934364499968 |
|---|---|
| author | Jalaeian-Farimani, Mohsen Xiong, Xiong Bascetta, Luca |
| author_facet | Jalaeian-Farimani, Mohsen Xiong, Xiong Bascetta, Luca |
| contents | This paper introduces a fuzzy reinforcement learning framework, Enhanced-FQL($λ$), that integrates novel Fuzzified Eligibility Traces (FET) and Segmented Experience Replay (SER) into fuzzy Q-learning with the Fuzzified Bellman Equation (FBE) for continuous control. The proposed approach employs an interpretable fuzzy rule base instead of complex neural architectures, while maintaining competitive performance through two key innovations: a fuzzified Bellman equation with eligibility traces for stable multi-step credit assignment, and a memory-efficient segment-based experience replay mechanism for enhanced sample efficiency. Theoretical analysis proves the proposed method convergence under standard assumptions. On the Cart--Pole benchmark, Enhanced-FQL($λ$) improves sample efficiency and reduces variance relative to $n$-step fuzzy TD and fuzzy SARSA($λ$), while remaining competitive with the tested DDPG baseline. These results support the proposed framework as an interpretable and computationally compact alternative for moderate-scale continuous control problems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_04392 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Enhanced-FQL($λ$), an Efficient and Interpretable RL with novel Fuzzy Eligibility Traces and Segmented Experience Replay Jalaeian-Farimani, Mohsen Xiong, Xiong Bascetta, Luca Machine Learning Artificial Intelligence Robotics Systems and Control Optimization and Control This paper introduces a fuzzy reinforcement learning framework, Enhanced-FQL($λ$), that integrates novel Fuzzified Eligibility Traces (FET) and Segmented Experience Replay (SER) into fuzzy Q-learning with the Fuzzified Bellman Equation (FBE) for continuous control. The proposed approach employs an interpretable fuzzy rule base instead of complex neural architectures, while maintaining competitive performance through two key innovations: a fuzzified Bellman equation with eligibility traces for stable multi-step credit assignment, and a memory-efficient segment-based experience replay mechanism for enhanced sample efficiency. Theoretical analysis proves the proposed method convergence under standard assumptions. On the Cart--Pole benchmark, Enhanced-FQL($λ$) improves sample efficiency and reduces variance relative to $n$-step fuzzy TD and fuzzy SARSA($λ$), while remaining competitive with the tested DDPG baseline. These results support the proposed framework as an interpretable and computationally compact alternative for moderate-scale continuous control problems. |
| title | Enhanced-FQL($λ$), an Efficient and Interpretable RL with novel Fuzzy Eligibility Traces and Segmented Experience Replay |
| topic | Machine Learning Artificial Intelligence Robotics Systems and Control Optimization and Control |
| url | https://arxiv.org/abs/2601.04392 |