mlsanityData to 7 Oct 2026

Noisy Networks for Exploration

arXiv 1706.10295 ↗First posted 30 Jun 2017cs.LG stat.MLcited by 262

Not on the map. Why?

Abstract (arXiv)

We introduce NoisyNet, a deep reinforcement learning agent with parametric noise added to its weights, and show that the induced stochasticity of the agent's policy can be used to aid efficient exploration. The parameters of the noise are learned with gradient descent along with the remaining network weights. NoisyNet is straightforward to implement and adds little computational overhead. We find that replacing the conventional exploration heuristics for A3C, DQN and dueling agents (entropy reward and ε-greedy respectively) with NoisyNet yields substantially higher scores for a wide range of Atari games, in some cases advancing the agent from sub to super-human performance.

Key facts. Cited by 262 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Jun 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 2; 2019: 1; 2020: 1; 2021: 61; 2022: 59; 2023: 39; 2024: 40; 2025: 37; 2026: 22.

262 papers.

Sort:

By area:

  1. 2021Randomized Ensembled Double Q-Learning: Learning Fast Without a Modelcited by 278
  2. 2022Exploration in Deep Reinforcement Learning: A Surveycited by 158
  3. 2023Bigger, Better, Faster: Human-level Atari with human-level efficiencycited by 145
  4. 2021Uncertainty Weighted Actor-Critic for Offline Reinforcement Learningcited by 125
  5. 2023Loss of Plasticity in Continual Deep Reinforcement Learningcited by 118
  6. 2021State Entropy Maximization with Random Encoders for Efficient Explorationcited by 107
  7. 2021Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentationcited by 101
  8. 2022BYOL-Explore: Exploration by Bootstrapped Predictioncited by 71
  9. 2022Automated Reinforcement Learning (AutoRL): A Survey and Open Problemscited by 69
  10. 2021A Survey of Exploration Methods in Reinforcement Learningcited by 68
  11. 2021Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspectivecited by 64
  12. 2021Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domaincited by 57
38 more
  1. 2021Randomized Exploration for Reinforcement Learning with General Value Function Approximationcited by 49
  2. 2021Adversarially Guided Actor-Criticcited by 47
  3. 2023DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimizationcited by 45
  4. 2023PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learningcited by 42
  5. 2021CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothingcited by 41
  6. 2021MADE: Exploration via Maximizing Deviation from Explored Regionscited by 40
  7. 2022SAM as an Optimal Relaxation of Bayescited by 40
  8. 2025Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifierscited by 40
  9. 2022Mask-based Latent Reconstruction for Reinforcement Learningcited by 39
  10. 2024In value-based deep reinforcement learning, a pruned network is a good networkcited by 38
  11. 2019An Optimistic Perspective on Offline Reinforcement Learningcited by 37
  12. 2021On Bonus-Based Exploration Methods in the Arcade Learning Environmentcited by 37
  13. 2018Sample-Efficient Imitation Learning via Generative Adversarial Netscited by 36
  14. 2021Zoo-Tuning: Adaptive Transfer from a Zoo of Modelscited by 35
  15. 2023Small batch deep reinforcement learningcited by 35
  16. 2022A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learningcited by 30
  17. 2023On the Importance of Exploration for Generalization in Reinforcement Learningcited by 30
  18. 2023Multi-agent Reinforcement Learning: A Comprehensive Surveycited by 30
  19. 2023Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlocited by 29
  20. 2021Offline Reinforcement Learning for Autonomous Driving with Safety and Exploration Enhancementcited by 28
  21. 2022The Phenomenon of Policy Churncited by 28
  22. 2025Roll the dice & look before you leap: Going beyond the creative limits of next-token predictioncited by 28
  23. 2021Principled Exploration via Optimistic Bootstrapping and Backward Inductioncited by 26
  24. 2022Sample Efficient Deep Reinforcement Learning via Uncertainty Estimationcited by 26
  25. 2022COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attackscited by 25
  26. 2022An information-theoretic perspective on intrinsic motivation in reinforcement learning: a surveycited by 25
  27. 2022Hyperbolic Deep Reinforcement Learningcited by 25
  28. 2025Rethinking Entropy Regularization in Large Reasoning Modelscited by 25
  29. 2022Investigating the Properties of Neural Network Representations in Reinforcement Learningcited by 24
  30. 2022Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?cited by 24
  31. 2022Redeeming Intrinsic Rewards via Constrained Optimizationcited by 24
  32. 2024Streaming Deep Reinforcement Learning Finally Workscited by 24
  33. 2021Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmarkcited by 23
  34. 2021Curiosity-Driven Exploration via Latent Bayesian Surprisecited by 22
  35. 2021Bayesian Sequential Optimal Experimental Design for Nonlinear Models Using Policy Gradient Reinforcement Learningcited by 22
  36. 2023Accelerating Reinforcement Learning with Value-Conditional State Entropy Explorationcited by 22
  37. 2023Latent Exploration for Reinforcement Learningcited by 21
  38. 2024On the consistency of hyper-parameter selection in value-based deep reinforcement learningcited by 21

50 most cited of 262 All 262 (JSON)