Playing Atari Space Invaders with Sparse Cosine Optimized Policy Evolution

TL;DR

This paper introduces SCOPE, a novel evolutionary approach that uses sparse cosine transforms to reduce input dimensionality, enabling effective learning in complex video game environments like Space Invaders.

Contribution

SCOPE applies DCT-based sparsification to improve evolutionary policy learning efficiency in high-dimensional game states.

Findings

SCOPE outperforms unmodified input evolutionary methods like OpenAI-ES and HyperNEAT.

SCOPE surpasses simple reinforcement learning methods such as DQN and A3C.

Input size is reduced by 53%, maintaining key features for effective policy learning.

Abstract

Evolutionary approaches have previously been shown to be effective learning methods for a diverse set of domains. However, the domain of game-playing poses a particular challenge for evolutionary methods due to the inherently large state space of video games. As the size of the input state expands, the size of the policy must also increase in order to effectively learn the temporal patterns in the game space. Consequently, a larger policy must contain more trainable parameters, exponentially increasing the size of the search space. Any increase in search space is highly problematic for evolutionary methods, as increasing the number of trainable parameters is inversely correlated with convergence speed. To reduce the size of the input space while maintaining a meaningful representation of the original space, we introduce Sparse Cosine Optimized Policy Evolution (SCOPE). SCOPE utilizes the Discrete Cosine Transform (DCT) as a pseudo attention mechanism, transforming an input state into a coefficient matrix. By truncating and applying sparsification to this matrix, we reduce the dimensionality of the input space while retaining the highest energy features of the original input. We demonstrate the effectiveness of SCOPE as the policy for the Atari game Space Invaders. In this task, SCOPE with CMA-ES outperforms evolutionary methods that consider an unmodified input state, such as OpenAI-ES and HyperNEAT. SCOPE also outperforms simple reinforcement learning methods, such as DQN and A3C. SCOPE achieves this result through reducing the input size by 53% from 33,600 to 15,625 then using a bilinear affine mapping of sparse DCT coefficients to policy actions learned by the CMA-ES algorithm.