The Paper concerns with the optimal behavior of agents in unknown computable environments, also known as universal artificial intelligence. These theoretical agents are able to learn to perform optimally in many types of environments. It is easy to work properly for an agent with known environment. If we sent this agent in unknown environment then will it work properly or not? Here I’ll try to build such an intelligent autonomous body which will try to give the proper response for unknown environment. This autonomous body (i.e. intelligent agent) will learn by itself for the unknown environment and will take appropriate action to that environment. Although they are able to optimally use prior information about the environment if it is available, in many cases they also learn to perform optimally in the absence of such information. Moreover, these agents can be proven to upper bound the performance of general purpose computable agents. Clearly such agents are extremely powerful and general, hence the name universal artificial intelligence. Here I’ll use the Hidden Markov Model (HMM) for observations for the various internal states.