Visual Radial Basis Q-Network
Julien Hautot, C\'eline Teuliere, Nourddine Azzaoui

TL;DR
This paper introduces a Radial Basis Function Network-based method for visual feature extraction in reinforcement learning, achieving comparable or better performance with fewer parameters compared to traditional deep learning approaches.
Contribution
The paper presents a novel RBFN-based approach for visual feature extraction in RL that requires fewer parameters and simplifies the process compared to convolutional or auto-encoder methods.
Findings
Achieves similar or better performance than deep CNNs and auto-encoders.
Uses fewer trainable parameters, simplifying the model.
Effective in Vizdoom environment for Q-learning tasks.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsQ-Learning
