Genes in Intelligent Agents

Training intelligent agents in Reinforcement Learning (RL) is much more time-consuming than animal learning. This is because agents learn from scratch, but animals learn with genes inherited from ancestors and are born with some innate abilities. Inspired by genes in animals, here we conceptualize the gene in intelligent agents and introduce Genetic Reinforcement Learning (GRL), a computational framework to represent, evaluate, and evolve genes (in agents). Leveraging GRL we identify genes and demonstrate several advantages of genes. First, we find that genes take the form of the fragment of agents' neural networks and can be inherited across generations. Second, we validate that genes bring better and stabler learning ability to agents, since genes condense knowledge from ancestors and bring agent with innate abilities. Third, we present evidence of Lamarckian evolution in intelligent agents. The continuous encoding of knowledge into genes across generations facilitates the evolution of genes. Overall, our work promotes a novel paradigm to train agents by incorporating genes.