Deep Reinforcement learning approach towards autonomous navigation and its challenges
Abstract
Reinforcement Learning (RL) is a subset of Machine Learning that trains an agent to make a series of decisions and take actions by interacting directly with the environment. In this approach the agent learns to attain the goal by the response from its actions as rewards or punishment. Recent advances in RL combined with deep learning methods have led to breakthrough research in solving many complex problems in the field of artificial intelligence. This paper presents recent literature in the area of autonomous visual navigation of robots using Deep Reinforcement Learning (DRL) algorithms and methods. In this paper, a proposal for developing a method to improve the learning capability of the agent is presented. This paper also describes the algorithms evaluated, the environment used for implementation and the policy applied to maximize the rewards earned by the agent.