High Performance Across Two Atari Paddle Games Using the Same Perceptual Control Architecture Without Training
This addresses the sample inefficiency problem in AI/robotics by proposing a non-learning alternative, though it is incremental as it applies an existing theory to a new domain.
The researchers tackled the problem of deep reinforcement learning requiring extensive training by developing a perceptual control theory model that requires no training samples or training time, achieving performance at least as high as DRL paradigms and close to good human performance across two Atari paddle games (Breakout and Pong).
Deep reinforcement learning (DRL) requires large samples and a long training time to operate optimally. Yet humans rarely require long periods training to perform well on novel tasks, such as computer games, once they are provided with an accurate program of instructions. We used perceptual control theory (PCT) to construct a simple closed-loop model which requires no training samples and training time within a video game study using the Arcade Learning Environment (ALE). The model was programmed to parse inputs from the environment into hierarchically organised perceptual signals, and it computed a dynamic error signal by subtracting the incoming signal for each perceptual variable from a reference signal to drive output signals to reduce this error. We tested the same model across two different Atari paddle games Breakout and Pong to achieve performance at least as high as DRL paradigms, and close to good human performance. Our study shows that perceptual control models, based on simple assumptions, can perform well without learning. We conclude by specifying a parsimonious role of learning that may be more similar to psychological functioning.