mlsanityData to 7 Oct 2026

PoPS: Policy Pruning and Shrinking for Deep Reinforcement Learning

arXiv 2001.05012 ↗First posted 14 Jan 2020cs.LG cs.AIcited by 30

Not on the map. Why?

Abstract (arXiv)

The recent success of deep neural networks (DNNs) for function approximation in reinforcement learning has triggered the development of Deep Reinforcement Learning (DRL) algorithms in various fields, such as robotics, computer games, natural language processing, computer vision, sensing systems, and wireless networking. Unfortunately, DNNs suffer from high computational cost and memory consumption, which limits the use of DRL algorithms in systems with limited hardware resources. In recent years, pruning algorithms have demonstrated considerable success in reducing the redundancy of DNNs in classification tasks. However, existing algorithms suffer from a significant performance reduction in the DRL domain. In this paper, we develop the first effective solution to the performance reduction problem of pruning in the DRL domain, and establish a working algorithm, named Policy Pruning and Shrinking (PoPS), to train DRL models with strong performance while achieving a compact representation of the DNN. The framework is based on a novel iterative policy pruning and shrinking method that leverages the power of transfer learning when training the DRL model. We present an extensive experimental study that demonstrates the strong performance of PoPS using the popular Cartpole, Lunar Lander, Pong, and Pacman environments. Finally, we develop an open source software for the benefit of researchers and developers in related fields.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Jan 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 4; 2023: 4; 2024: 9; 2025: 6; 2026: 2.

30 papers.

Sort:

By area:

  1. 2022The State of Sparse Training in Deep Reinforcement Learningcited by 60
  2. 2021Dynamic Sparse Training for Deep Reinforcement Learningcited by 49
  3. 2021Zero Time Waste: Recycling Predictions in Early Exit Neural Networkscited by 39
  4. 2024In value-based deep reinforcement learning, a pruned network is a good networkcited by 38
  5. 2022RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratchcited by 30
  6. 2021Single-Shot Pruning for Offline Reinforcement Learningcited by 21
  7. 2024Neuroplastic Expansion in Deep Reinforcement Learningcited by 17
  8. 2023Parameter Sharing with Network Pruning for Scalable Multi-Agent Deep Reinforcement Learningcited by 13
  9. 2021Deep Reinforcement Learning for Simultaneous Sensing and Channel Access in Cognitive Networkscited by 8
  10. 2021GST: Group-Sparse Training for Accelerating Deep Reinforcement Learningcited by 7
  11. 2024The Impact of Quantization and Pruning on Deep Reinforcement Learning Modelscited by 6
  12. 2025Eau De Q-Network: Adaptive Distillation of Neural Networks in Deep Reinforcement Learningcited by 6
18 more
  1. 2022Rate-Constrained Remote Contextual Banditscited by 5
  2. 2024Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learningcited by 5
  3. 2023Deep Multi-Agent Reinforcement Learning for Decentralized Active Hypothesis Testingcited by 4
  4. 2024Tiny Multi-Agent DRL for Twins Migration in UAV Metaverses: A Multi-Leader Multi-Follower Stackelberg Game Approachcited by 4
  5. 2022Multi-Agent Deep Reinforcement Learning for Cost- and Delay-Sensitive Virtual Network Function Placement and Routingcited by 3
  6. 2024Compressing Deep Reinforcement Learning Networks with a Dynamic Structured Pruning Method for Autonomous Drivingcited by 3
  7. 2023Sparse Training for Federated Learning with Regularized Error Correctioncited by 2
  8. 2025Sparsity-Driven Plasticity in Multi-Task Reinforcement Learningcited by 2
  9. 2024Tiny Reinforcement Learning for Quadruped Locomotion using Decision Transformerscited by 1
  10. 2024Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Trainingcited by 1
  11. 2025Multi-Agent Actor-Critic with Harmonic Annealing Pruning for Dynamic Spectrum Access Systemscited by 1
  12. 2023A Masked Pruning Approach for Dimensionality Reduction in Communication-Efficient Federated Learning Systemscited by 0
  13. 2024Learning Emergence of Interaction Patterns across Independent RL Agents in Multi-Agent Environmentscited by 0
  14. 2025Bi-LSTM based Multi-Agent DRL with Computation-aware Pruning for Agent Twins Migration in Vehicular Embodied AI Networkscited by 0
  15. 2025Searching for a Hidden Markov Anomaly over Multiple Processescited by 0
  16. 2025Control-Optimized Deep Reinforcement Learning for Artificially Intelligent Autonomous Systemscited by 0
  17. 2026RNM-TD3: N:M Semi-structured Sparse Reinforcement Learning From Scratchcited by 0
  18. 2026A Closed-Loop Evaluation of Capability Loss and Recovery in Compressed Driving Policiescited by 0