The Significance of Temporal-Difference Learning in Self-Play Training TD-Rummy versus EVO-rummy

Reinforcement learning has been used for training game playing agents. The value function for a complex game must be approximated with a continuous function because the number of states becomes too large to enumerate. Temporal-difference learning with self-play is one method successfully used to derive the value approximation function. Coevolution of the value function is also claimed to yield good results. This paper reports on a direct comparison between an agent trained to play gin rummy using temporal difference learning, and the same agent trained with co-evolution. Coevolution produced superior results.