mlsanityData to 14 Oct 2026

Fuzzy Logic Theory-based Adaptive Reward Shaping for Robust Reinforcement Learning (FARS)

arXiv 2604.15772 ↗First posted 17 Apr 2026cs.ROcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 9 of its 29 references that are in the map. First posted on arXiv 17 Apr 2026.

Builds on

9 of 29 references.

References · 9

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2017Differential Flatness of Quadrotor Dynamics Subject to Rotor Drag for Accurate Tracking of High-Speed Trajectoriescited by 32
  3. 2022PencilNet: Zero-Shot Sim-to-Real Transfer Learning for Robust Gate Perception in Autonomous Drone Racingcited by 8
  4. 2022Event-based Navigation for Autonomous Drone Racing with Sparse Gated Recurrent Networkcited by 7
  5. 2024Environment as Policy: Learning to Race in Unseen Trackscited by 6
  6. 2025Mastering Diverse, Unknown, and Cluttered Tracks for Robust Vision-Based Drone Racingcited by 3
  7. 2020Image Generation for Efficient Neural Network Training in Autonomous Drone Racingcited by 2
  8. 2023Contact Energy Based Hindsight Experience Prioritizationcited by 2
  9. 2024Continual Learning for Robust Gate Detection under Dynamic Lighting in Autonomous Drone Racingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Fuzzy Logic Guided Reward Function Variation: An Oracle for Testing Reinforcement Learning Programs
  2. 2024Comprehensive Overview of Reward Engineering and Shaping in Advancing Reinforcement Learning Applications
  3. 2026A Unified Framework for Dynamic Reward Shaping in Reinforcement Learning
  4. 2026Zero-Shot, Safe and Time-Efficient UAV Navigation via Potential-Based Reward Shaping, Control Lyapunov and Barrier Functions
  5. 2025Logic-based Task Representation and Reward Shaping in Multiagent Reinforcement Learning ↗
  6. 2024Adaptive Reward Design for Reinforcement Learning
  7. 2024Dense Dynamics-Aware Reward Synthesis: Integrating Prior Experience with Demonstrations
  8. 2024Learning Robust Reward Machines from Noisy Labels