Hybrid fuzzy AHP–TOPSIS approach to prioritizing solutions for inverse reinforcement learning

Abstract

Reinforcement learning (RL) techniques nurture building up solutions for sequential decision-making problems under uncertainty and ambiguity. RL has agents with a reward function that interacts with a dynamic environment to find out an optimal policy. There are problems associated with RL like the reward function should be specified in advance, design difficulties and unable to handle large complex problems, etc. This led to the development of inverse reinforcement learning (IRL). IRL also suffers from many problems in real life like robust reward functions, ill-posed problems, etc., and different solutions have been proposed to solve these problems like maximum entropy, support for multiple rewards and non-linear reward functions, etc. There are majorly eight problems associated with IRL and eight solutions have been proposed to solve IRL problems. This paper has proposed a hybrid fuzzy AHP–TOPSIS approach to prioritize the solutions while implementing IRL. Fuzzy Analytical Hierarchical Process (FAHP) is used to get the weights of identified problems. The relative accuracy and root-mean-squared error using FAHP are 97.74 and 0.0349, respectively. Fuzzy Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) uses these FAHP weights to prioritize the solutions. The most significant problem in IRL implementation is of ‘lack of robust reward functions’ weighting 0.180, whereas the most significant solution in IRL implementation is ‘Supports optimal policy and rewards functions along with stochastic transition models’ having closeness of coefficient (CofC) value of 0.967156846.

UMobileNetV2 model for semantic segmentation of gastrointestinal tract in MRI scans

“…Montalbo et al [ 24 ] recommended the Multi-Fused Residual CNN (MFuRe-CNN) for analyzing endoscopic images of GI illnesses using the Kvasir dataset in 2022. Gibson et al reported a neural network design for segmentation of eight organs [ 25 ]. The pancreas, digestive system, "esophagus, stomach, and duodenum," are all necessary for endoscopic referral to the biliary and pancreatic processes.…”

Fuzzy TOPSIS and Fuzzy AHP-based MCDA for selecting the Optimal Location for a Solar PV-powered RO Desalination Unit in Visakhapatnam, India

“…The Specific Energy Consumption (SEC) of a RO desalination plant can be determined by local water demand, water quality, first year of operation, and energy source. A mathematical model can be created to optimize SEC, bearing in mind retentate pressure drop and membrane capacity demand ratio [21][22][23][24][25][26][27][28][29][30][31][32][33][34]. The choice of the energy source, e.g.…”

“…By combining these two methods, decision makers can effectively assess and prioritize alternatives based on multiple criteria, considering both qualitative and quantitative factors. This approach has been applied in various domains, such as solid waste management [23] and supplier evaluation and selection [24].…”

“…Fuzzy Techniques for Prioritization by Similarity to Ideal Solutions (Fuzzy TOPSIS) and Fuzzy Analytical Hierarchy Process (Fuzzy AHP) excel at handling imprecise and ambiguous data and provide a framework robust and adaptable for evaluating complex systems with different and sometimes conflicting criteria [21][22][23][24][25].…”