• Gajanan K. Bhoi
• G. A. Patil
• Umesh Kulkarni

In the last few years it has been brought into notice a complex issue of optimization systems that help track activities and provide outputs to analyze a certain pattern and predict behavior and possibilities to understand any kind of system. Such kind of problem solving can be done with help of Deep Deterministic Policy Gradient Optimization (DDPGO). DDPGO is nothing but a technique that is made up by combining two different approaches i.e. Deep Q-Network and Deterministic Policy Gradient. It mainly consists of two major parts actor and critic. The Actor is an arrangement network that accepts the state as info and results the specific activity (persistent), rather than a likelihood appropriation over activities. The Critic is a Q-esteem network that makes an in state and move as info and results the Q-esteem. DDPG is an "off"- approach technique. DDPG is utilized in the consistent activity setting and the "deterministic" in DDPG alludes to the way that the Actor processes the activity straightforwardly rather than a likelihood circulation over activities.

DDPGO, Deep Learning Neural Network,DDPG

"Survey on different techniques that use DDPGO with their implementation", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 8, page no.d229-d231, August-2022, Available :http://www.jetir.org/papers/JETIR2208328.pdf

"Survey on different techniques that use DDPGO with their implementation", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 8, page no. ppd229-d231, August-2022, Available at : http://www.jetir.org/papers/JETIR2208328.pdf