Our system aims to better and feather enhance the chatbot technology through making it a smart behavioral one that can carry a conversation smoothly and efficiently with humans using Deep Reinforcement Learning, Image and video processing .Through conversing with said human it can not only process his/her words with remarkable accuracy but also their behavior during said words (ex. Angry ,sad , frustrated )through image and voice processing to reply accordingly in which our system will go through different sources and then compile together the most fitting reply/answer through the use of deep reinforcement learning giving the user the feeling that he/she is talking to a conscious human being.Input wise The user will use a video camera and a microphone to converse with our chatbot.After that the system will extract the frames and audio out of the video so that we can have our data.The processing of both the audio and the frames acquired from the live video will be simultaneous. Using speech recognition the system will turn the spoken words into text (string) form so that the system can understand what the user's inquiry is about. Analyze user speech to extract vocal sentimental features by analyzing multiple physical proprieties of the voice said famously the "Empath" AI uses such technique. Then on the other side the system will make use of face detection techniques / algorithms to locate the face making extracting information about his/her stat easier . Through the use of machine learning the system will be able to detect the user emotions using techniques such as recognize feature point acquired from the user's face in order to detect his/her emotional stat across the duration that he/she is conversing with the system bot and comparing them to our dataset.Finally through the use of the data we collected and deep reinforcement learning the user will be presented with the most fitting reply that will make the conversation between him/her and the system bot flow smoothly as if it was carried by a human.