Planning with Incomplete Knowledge and Uncertain Goals: A Comparative Evaluation

Reinforcement learning makes the system more accurate and on real real-time basis and the competence sets work with the decision-making process and the learning of the model can be done by calculating the rewards. Created an application that is equipped with the Markov decision process along with reinforcement learning where the agent can understand the patterns of the nutritional chart. The set will be selected and the planner will provide the plan of activities that are used to perform. The plan of events can be made on the agent's process mechanism which will followed by the application. The autonomous car will work on an agent knowledge base where the rewards system will properly plan events. The Monte Carlo Tree Search (MCTS) MCTS is used to make optimal decisions in artificial intelligence problems by performing random simulations of future events. In this paper we present a comparative evaluation of planning methods and as an application the improvement of the weak method by using features from strong ones.