A new soft computing method for integration of expert's knowledge in reinforcement learn-ing problems

2021/06/13 by Mohsen Annabestani, Annabestani, Mohsen, Ali Abedi +6
Computer Science · #Adaptive Dynamic Programming Control #Artificial Intelligence (cs.AI) #Evolutionary Algorithms and Applications #FOS: Computer and information sciences #Reinforcement Learning in Robotics #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.2106.07088

openalex publication_date 2021/06/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper proposes a novel fuzzy action selection method to leverage human knowledge in reinforcement learning problems. Based on the estimates of the most current action-state values, the proposed fuzzy nonlinear mapping as-signs each member of the action set to its probability of being chosen in the next step. A user tunable parameter is introduced to control the action selection policy, which determines the agent's greedy behavior throughout the learning process. This parameter resembles the role of the temperature parameter in the softmax action selection policy, but its tuning process can be more knowledge-oriented since this parameter reflects the human knowledge into the learning agent by making modifications in the fuzzy rule base. Simulation results indicate that including fuzzy logic within the reinforcement learning in the proposed manner improves the learning algorithm's convergence rate, and provides superior performance.

Related

• Reinforcement Learning Based on Active Learning Method
• Reinforcement Learning of an Interpretable Fuzzy System Through a Neural Fuzzy Actor-Critic Framework for Mobile Robot Control
• KoGuN: Accelerating Deep Reinforcement Learning via Integrating Human Suboptimal Knowledge
• A Survey of Reinforcement Learning Techniques: Strategies, Recent Development, and Future Directions
• How to Choose a Reinforcement-Learning Algorithm