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

2021-06-13 · Mohsen Annabestani, Ali Abedi, Mohammad Reza Nematollahi, Mohammad Bagher Naghibi Sis-tani

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.

📄 PDF Abstract BibTeX arXiv:2106.07088

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Pretrain Soft Q-Learning with Imperfect Demonstrations

2019-05-09 · Xiaoqin Zhang, Yunfei Li, Huimin Ma, Xiong Luo

Pretraining reinforcement learning methods with demonstrations has been an important concept in the study of reinforcement learning since a large amount of computing power is spent on online simulations with existing rei…

Q-Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Report of the 2025 Workshop on Next-Generation Ecosystems for Scientific Computing: Harnessing Community, Software, and AI for Cross-Disciplinary Team Science

2025-10-03 · Lois Curfman McInnes, Dorian Arnold, Prasanna Balaprakash, Mike Bernhardt 외 arxiv

This report summarizes insights from the 2025 Workshop on Next-Generation Ecosystems for Scientific Computing: Harnessing Community, Software, and AI for Cross-Disciplinary Team Science, which convened more than 40 exper…

Coral: A Unifying Abstraction Layer for Composable Robotics Software

2025-09-02 · Steven Swanbeck, Mitch Pryor arxiv

Despite the multitude of excellent software components and tools available in the robotics and broader software engineering communities, successful integration of software for robotic systems remains a time-consuming and…

One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents

2026-09-20 · Jie Zhao, Ziyu Jiang, Suhang Zheng, Minghui Shan 외 hf

Repository-level software engineering (SWE) comprises heterogeneous task categories, whose progress under pooled agentic reinforcement learning can be uneven: gains in some categories coincide with regressions in others,…

Reinforcement Learning

$n$-Musketeers: Reinforcement Learning Shapes Collaboration Among Language Models

2026-02-09 · Ryozo Masukawa, Sanggeon Yun, Hyunwoo Oh, SuhgHeon Jeong 외 arxiv

Recent progress in reinforcement learning with verifiable rewards (RLVR) shows that small, specialized language models (SLMs) can exhibit structured reasoning without relying on large monolithic LLMs. We introduce soft h…