mlsanityData to 7 Oct 2026

DNS: Determinantal Point Process Based Neural Network Sampler for Ensemble Reinforcement Learning

arXiv 2201.13357 ↗First posted 31 Jan 2022cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Application of ensemble of neural networks is becoming an imminent tool for advancing the state-of-the-art in deep reinforcement learning algorithms. However, training these large numbers of neural networks in the ensemble has an exceedingly high computation cost which may become a hindrance in training large-scale systems. In this paper, we propose DNS: a Determinantal Point Process based Neural Network Sampler that specifically uses k-dpp to sample a subset of neural networks for backpropagation at every training step thus significantly reducing the training time and computation cost. We integrated DNS in REDQ for continuous control tasks and evaluated on MuJoCo environments. Our experiments show that DNS augmented REDQ outperforms baseline REDQ in terms of average cumulative reward and achieves this using less than 50% computation when measured in FLOPS.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 20 of its 48 references that are in the map. First posted on arXiv 31 Jan 2022.

Builds on

20 of 48 references.

References · 20

  1. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
  2. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,704
  3. 2019Similarity of Neural Network Representations Revisitedcited by 1,695
  4. 2019Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reductioncited by 833
  5. 2016Deep Exploration via Bootstrapped DQNcited by 518
  6. 2019Model-Based Reinforcement Learning for Ataricited by 495
  7. 2021Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemblecited by 297
  8. 2021Randomized Ensembled Double Q-Learning: Learning Fast Without a Modelcited by 278
  9. 2020SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learningcited by 150
  10. 2020Maxmin Q-learning: Controlling the Estimation Bias of Q-learningcited by 117
  11. 2020Effective Diversity in Population Based Reinforcement Learningcited by 116
  12. 2016Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learningcited by 106
8 more
  1. 2021Tactical Optimism and Pessimism for Deep Reinforcement Learningcited by 55
  2. 2021Deep Reinforcement Learning for the Control of Robotic Manipulation: A Focussed Mini-Reviewcited by 34
  3. 2016Query-Focused Extractive Video Summarizationcited by 26
  4. 2022Sample Efficient Deep Reinforcement Learning via Uncertainty Estimationcited by 26
  5. 2017Creating Capsule Wardrobes from Fashion Imagescited by 24
  6. 2019Exact sampling of determinantal point processes with sublinear time preprocessingcited by 19
  7. 2016Fast DPP Sampling for Nystr"om with Application to Kernel Methodscited by 15
  8. 2018ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Searchcited by 12

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 3; 2025: 2.

8 papers.

  1. 2022Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Sizecited by 20
  2. 2023Ensemble Reinforcement Learning: A Surveycited by 16
  3. 2024SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learningcited by 8
  4. 2023Diversity from Human Feedbackcited by 5
  5. 2024Fusion-PSRO: Nash Policy Fusion for Policy Space Response Oraclescited by 2
  6. 2025Diverse Mini-Batch Selection in Reinforcement Learning for Efficient Chemical Exploration in de novo Drug Designcited by 1
  7. 2024Heuristic Algorithm-based Action Masking Reinforcement Learning (HAAM-RL) with Ensemble Inference Methodcited by 0
  8. 2025Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategiescited by 0