Optimal Control with Natural Images: Efficient Reinforcement Learning using Overcomplete Sparse Codes

arXiv:2412.08893 · cs.LG, cs.AI, cs.SY, eess.SY · Submitted 2024-12-12 · Read on arXiv

cs.LG, cs.AI, cs.SY, eess.SY

Submitted: 2024-12-12

Updated: 2026-05-05

DOI: 10.1016/j.neucom.2026.134840

Code: https://github.com/ploxley/efficient-RL-for-images

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 68× in this paper · explained in 2 episodes
• Reinforcement Learning — 51× in this paper · explained in 4 episodes
• Redundancy — 2× in this paper · explained in 2 episodes
• Sparsity — 2× in this paper · explained in 4 episodes
• Copula — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Stochastic Dynamics — 1× in this paper · explained in 2 episodes

Sources

• Convergence Analysis for Deep Sparse Coding via Convolutional Neural Networks
• The Utility of Sparse Representations for Control in Reinforcement Learning
• Learning sparse representations in reinforcement learning
• Natural Environment Benchmarks for Reinforcement Learning
• Learning Invariant Representations for Reinforcement Learning without Reconstruction

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks