Computational simulation of language evolution provides valuable insights into the origin of language. Simulating the evolution of language among agents in an artificial world also presents an interesting challenge in evolutionary computation and machine learning. In this paper, a jungle world is constructed where agents must accomplish different tasks such as hunting and mating by evolving their own language to coordinate their actions. In addition, all agents must acquire the language during their lifetime through interaction with other agents. This paper proposes the algorithm of Evolutionary Reinforcement Learning with Potentiation and Memory (ERL-POM) as a computational approach for achieving this goal. Experimental results show that ERL-POM is effective in situated simulation of language evolution, demonstrating that languages can be evolved in the artificial environment when communication is necessary for some or all of the tasks the agents perform.