mlsanityData to 14 Oct 2026

Hard-Thresholding Meets Evolution Strategies in Reinforcement Learning

arXiv 2405.01615 ↗First posted 2 May 2024cs.NE cs.LGcited by 0

On the map: Deep reinforcement learning methods → RL for games and combinatorial optimization

Abstract (arXiv)

Evolution Strategies (ES) have emerged as a competitive alternative for model-free reinforcement learning, showcasing exemplary performance in tasks like Mujoco and Atari. Notably, they shine in scenarios with imperfect reward functions, making them invaluable for real-world applications where dense reward signals may be elusive. Yet, an inherent assumption in ES, that all input features are task-relevant, poses challenges, especially when confronted with irrelevant features common in real-world problems. This work scrutinizes this limitation, particularly focusing on the Natural Evolution Strategies (NES) variant. We propose NESHT, a novel approach that integrates Hard-Thresholding (HT) with NES to champion sparsity, ensuring only pertinent features are employed. Backed by rigorous analysis and empirical tests, NESHT demonstrates its promise in mitigating the pitfalls of irrelevant features and shines in complex decision-making problems like noisy Mujoco and Atari tasks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods. Builds on 15 of its 29 references that are in the map. First posted on arXiv 2 May 2024.

Builds on

15 of 29 references.

References · 15

  1. 2015Trust Region Policy Optimizationcited by 2,580
  2. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  3. 2020What is the State of Neural Network Pruning?cited by 583
  4. 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 574
  5. 2016Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activationscited by 426
  6. 2017Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learningcited by 150
  7. 2021Dynamic Sparse Training for Deep Reinforcement Learningcited by 49
  8. 2021Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Surveycited by 28
  9. 2015How to Discount Deep Reinforcement Learning: Towards New Dynamic Strategiescited by 27
  10. 2021Structured Sparsity Inducing Adaptive Optimizers for Deep Learningcited by 17
  11. 2021Derivative-Free Reinforcement Learning: A Reviewcited by 15
  12. 2019Non-asymptotic Analysis of Stochastic Methods for Non-Smooth Non-Convex Regularized Problemscited by 14
3 more
  1. 2014Linear Convergence of Stochastic Iterative Greedy Algorithms with Sparse Constraintscited by 13
  2. 2023Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learningcited by 13
  3. 2022Survey: Exploiting Data Redundancy for Optimization of Deep Learningcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Solving Deep Reinforcement Learning Tasks with Evolution Strategies and Linear Policy Networks
  2. 2025Exploration by Random Reward Perturbation
  3. 2022On Practical Reinforcement Learning: Provable Robustness, Scalability, and Statistical Efficiency
  4. 2024Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms
  5. 2025Utilizing Novelty-based Evolution Strategies to Train Transformers in Reinforcement Learning
  6. 2026Continual Reinforcement Learning with Neuroevolution
  7. 2025Evolutionary Policy Optimization
  8. 2026Evolutionary Discovery of Reinforcement Learning Algorithms via Large Language Models