mlsanityData to 14 Oct 2026

Deep Reinforcement Learning with Plasticity Injection

arXiv 2305.15555 ↗First posted 24 May 2023cs.LG cs.AIcited by 74

Not on the map. Why?

Cited by 44 in Deep reinforcement learning methods, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

A growing body of evidence suggests that neural networks employed in deep reinforcement learning (RL) gradually lose their plasticity, the ability to learn from new data; however, the analysis and mitigation of this phenomenon is hampered by the complex relationship between plasticity, exploration, and performance in RL. This paper introduces plasticity injection, a minimalistic intervention that increases the network plasticity without changing the number of trainable parameters or biasing the predictions. The applications of this intervention are two-fold: first, as a diagnostic tool unicodex2014 if injection increases the performance, we may conclude that an agent's network was losing its plasticity. This tool allows us to identify a subset of Atari environments where the lack of plasticity causes performance plateaus, motivating future studies on understanding and combating plasticity loss. Second, plasticity injection can be used to improve the computational efficiency of RL training if the agent has to re-learn from scratch due to exhausted plasticity or by growing the agent's network dynamically without compromising performance. The results on Atari show that plasticity injection attains stronger performance compared to alternative methods while being computationally efficient.

Key facts. Cited by 74 papers in the map (data through 14 Oct 2026). Builds on 40 of its 74 references that are in the map. First posted on arXiv 24 May 2023.

Builds on

40 of 74 references.

References · 40

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  5. 2015Continuous control with deep reinforcement learningcited by 3,407
  6. 2015Trust Region Policy Optimizationcited by 2,580
  7. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  8. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  9. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,745
  10. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  11. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,546
  12. 2016Progressive Neural Networkscited by 1,361
28 more
  1. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
  2. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 883
  3. 2022A Generalist Agentcited by 808
  4. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 807
  5. 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 786
  6. 2017A Distributional Perspective on Reinforcement Learningcited by 765
  7. 2019Model-Based Reinforcement Learning for Ataricited by 502
  8. 2015Neural Module Networkscited by 376
  9. 2015Net2Net: Accelerating Learning via Knowledge Transfercited by 250
  10. 2022The Primacy Bias in Deep Reinforcement Learningcited by 247
  11. 2018Deep Reinforcement Learning and the Deadly Triadcited by 174
  12. 2023The Dormant Neuron Phenomenon in Deep Reinforcement Learningcited by 174
  13. 2023Understanding plasticity in neural networkscited by 174
  14. 2023Human-Timescale Adaptation in an Open-Ended Task Spacecited by 138
  15. 2020Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learningcited by 134
  16. 2022Understanding and Preventing Capacity Loss in Reinforcement Learningcited by 125
  17. 2023Loss of Plasticity in Continual Deep Reinforcement Learningcited by 121
  18. 2021Continual Backprop: Stochastic Gradient Descent with Persistent Randomnesscited by 80
  19. 2020Transient Non-Stationarity and Generalisation in Deep Reinforcement Learningcited by 75
  20. 2021Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspectivecited by 65
  21. 2022Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progresscited by 65
  22. 2020The Value-Improvement Path: Towards Better Representations for Reinforcement Learningcited by 60
  23. 2022Architecture Matters in Continual Learningcited by 46
  24. 2021A study on the plasticity of neural networkscited by 44
  25. 2023Efficient Deep Reinforcement Learning Requires Regulating Overfittingcited by 36
  26. 2022An Empirical Study of Implicit Regularization in Deep Offline RLcited by 24
  27. 2019Benchmarking Bonus-Based Exploration Methods on the Arcade Learning Environmentcited by 17
  28. 2023Towards Deployable RL -- What's Broken with RL Research and a Potential Fixcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 7; 2024: 25; 2025: 19; 2026: 23.

74 papers.

Sort:

By area:

  1. 2024Disentangling the Causes of Plasticity Loss in Neural Networkscited by 86
  2. 2023Maintaining Plasticity in Continual Learning via Regenerative Regularizationcited by 65
  3. 2024Normalization and effective learning rates in reinforcement learningcited by 58
  4. 2024Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learningcited by 50
  5. 2024Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learningcited by 50
  6. 2023DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimizationcited by 47
  7. 2023Maintaining Plasticity in Deep Continual Learningcited by 43
  8. 2023Improving Language Plasticity via Pretraining with Active Forgettingcited by 43
  9. 2024In value-based deep reinforcement learning, a pruned network is a good networkcited by 39
  10. 2023Continual Learning as Computationally Constrained Reinforcement Learningcited by 37
  11. 2024Weight Clipping for Deep Continual and Reinforcement Learningcited by 29
  12. 2023Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stagescited by 28
38 more
  1. 2024No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPOcited by 27
  2. 2023Resetting the Optimizer in Deep RL: An Empirical Studycited by 26
  3. 2024A Study of Plasticity Loss in On-Policy Deep Reinforcement Learningcited by 26
  4. 2024Plasticity Loss in Deep Reinforcement Learning: A Surveycited by 24
  5. 2025Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churncited by 22
  6. 2024Parseval Regularization for Continual Reinforcement Learningcited by 21
  7. 2024Neuroplastic Expansion in Deep Reinforcement Learningcited by 18
  8. 2024Dissecting Deep RL with High Update Ratios: Combatting Value Divergencecited by 17
  9. 2024Fast TRAC: A Parameter-Free Optimizer for Lifelong Reinforcement Learningcited by 17
  10. 2024ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularizationcited by 16
  11. 2024MAD-TD: Model-Augmented Data stabilizes High Update Ratio RLcited by 16
  12. 2024Can Learned Optimization Make Reinforcement Learning Less Difficult?cited by 14
  13. 2025Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learningcited by 14
  14. 2024Position: Lifetime tuning is incompatible with continual reinforcement learningcited by 11
  15. 2024Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timestepscited by 11
  16. 2025A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Controlcited by 9
  17. 2025On-device edge learning for IoT data streams: a surveycited by 8
  18. 2025Multi-Task Reinforcement Learning Enables Parameter Scalingcited by 8
  19. 2025What Can Grokking Teach Us About Learning Under Nonstationarity?cited by 8
  20. 2024DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticitycited by 7
  21. 2025SPEQ: Offline Stabilization Phases for Efficient Q-Learning in High Update-To-Data Ratio Reinforcement Learningcited by 7
  22. 2026FIRE: Frobenius-Isometry Reinitialization for Balancing the Stability-Plasticity Tradeoffcited by 7
  23. 2024Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learningcited by 6
  24. 2025Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Losscited by 6
  25. 2025Reinitializing weights vs units for maintaining plasticity in neural networkscited by 6
  26. 2025Experience Replay Addresses Loss of Plasticity in Continual Learningcited by 4
  27. 2026Predicting Plasticity in Deep Continual Learning: A Theoretical Perspectivecited by 4
  28. 2024Diverse Feature Learning by Self-distillation and Resetcited by 2
  29. 2024Mitigating the Stability-Plasticity Dilemma in Adaptive Train Scheduling with Curriculum-Driven Continual DQN Expansioncited by 2
  30. 2025Plasticine: Accelerating Research in Plasticity-Motivated Deep Reinforcement Learningcited by 2
  31. 2025Preserving Plasticity in Continual Learning with Adaptive Linearity Injectioncited by 2
  32. 2025Sparsity-Driven Plasticity in Multi-Task Reinforcement Learningcited by 2
  33. 2025AltNet: Addressing the Plasticity-Stability Dilemma in Reinforcement Learningcited by 2
  34. 2026What Does Flow Matching Bring To TD Learning?cited by 2
  35. 2026The Rank and Gradient Lost in Non-stationarity: Sample Weight Decay for Mitigating Plasticity Loss in Reinforcement Learningcited by 2
  36. 2026Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClawcited by 2
  37. 2024Hadamard Representation: Scaffolding Performance Across Model-free RLcited by 1
  38. 2024Maintain Plasticity in Long-timescale Continual Test-time Adaptationcited by 1

50 most cited of 74 All 74 (JSON)