Enhancing Two-Player Performance Through Single-Player Knowledge Transfer: An Empirical Study on Atari 2600 Games
This addresses the problem of unstable and inefficient training in two-player reinforcement learning for game developers and AI researchers, though it is incremental as it builds on existing transfer learning methods.
The study tackled the challenge of training reinforcement learning agents for two-player games by leveraging knowledge from single-player versions, showing improved training efficiency and performance in ten Atari 2600 environments with measures like reduced training time and higher average rewards.
Playing two-player games using reinforcement learning and self-play can be challenging due to the complexity of two-player environments and the possible instability in the training process. We propose that a reinforcement learning algorithm can train more efficiently and achieve improved performance in a two-player game if it leverages the knowledge from the single-player version of the same game. This study examines the proposed idea in ten different Atari 2600 environments using the Atari 2600 RAM as the input state. We discuss the advantages of using transfer learning from a single-player training process over training in a two-player setting from scratch, and demonstrate our results in a few measures such as training time and average total reward. We also discuss a method of calculating RAM complexity and its relationship to performance.