Open AccessA Hybrid Algorithm in Reinforcement Learning for Crowd Simulation
Author(s) -
K. Pavithra,
G. Radhamani
Publication year - 2020
Publication title -
international journal of recent technology and engineering
Language(s) - English
Resource type - Journals
ISSN - 2277-3878
DOI - 10.35940/ijrte.f9187.038620
Subject(s) - reinforcement learning , computer science , bellman equation , function (biology) , crowd simulation , stability (learning theory) , value (mathematics) , q learning , tracking (education) , artificial intelligence , algorithm , function approximation , crowd psychology , machine learning , mathematical optimization , artificial neural network , mathematics , crowds , psychology , pedagogy , computer security , evolutionary biology , biology
Exploiting the efficiency and stability of Dynamic Crowd, the paper proposes a hybrid crowd simulation algorithm that runs using multi agents and it mainly focuses on identifying the crowd to simulate. An efficient measurement for both static and dynamic crowd simulation is applied in tracking and transportation applications. The proposed Hybrid Agent Reinforcement Learning (HARL) algorithm combines the Q-Learning off-policy value function and SARSA algorithm on-policy value function, which is used for dynamic crowd evacuation scenario. The HARL algorithm performs multiple value functions and combines the policy value function derived from the multi agent to improve the performance. In addition, the efficiency of the HARL algorithm is able to demonstrate in varied crowd sizes. Two kinds of applications are used in Reinforcement Learning such as tracking applications and transportation monitoring applications for pretending the crowd sizes.