Visual Radial Basis Q-Network
This addresses the need for simpler and more parameter-efficient methods in visual reinforcement learning, though it appears incremental as it builds on existing Q-learning frameworks.
The paper tackled the problem of high input dimension in reinforcement learning from raw images by proposing a Radial Basis Function Network (RBFN) to extract sparse features with few trainable parameters, achieving similar or better performance than Deep Q-Networks in the Vizdoom environment.
While reinforcement learning (RL) from raw images has been largely investigated in the last decade, existing approaches still suffer from a number of constraints. The high input dimension is often handled using either expert knowledge to extract handcrafted features or environment encoding through convolutional networks. Both solutions require numerous parameters to be optimized. In contrast, we propose a generic method to extract sparse features from raw images with few trainable parameters. We achieved this using a Radial Basis Function Network (RBFN) directly on raw image. We evaluate the performance of the proposed approach for visual extraction in Q-learning tasks in the Vizdoom environment. Then, we compare our results with two Deep Q-Network, one trained directly on images and another one trained on feature extracted by a pretrained auto-encoder. We show that the proposed approach provides similar or, in some cases, even better performances with fewer trainable parameters while being conceptually simpler.