mlsanityData to 7 Oct 2026

Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks

arXiv 2406.02596 ↗First posted 1 Jun 2024cs.LG cs.AIcited by 40

Not on the map. Why?

Abstract (arXiv)

This study investigates the loss of generalization ability in neural networks, revisiting warm-starting experiments from Ash & Adams. Our empirical analysis reveals that common methods designed to enhance plasticity by maintaining trainability provide limited benefits to generalization. While reinitializing the network can be effective, it also risks losing valuable prior knowledge. To this end, we introduce the Hare & Tortoise, inspired by the brain's complementary learning system. Hare & Tortoise consists of two components: the Hare network, which rapidly adapts to new information analogously to the hippocampus, and the Tortoise network, which gradually integrates knowledge akin to the neocortex. By periodically reinitializing the Hare network to the Tortoise's weights, our method preserves plasticity while retaining general knowledge. Hare & Tortoise can effectively maintain the network's ability to generalize, which improves advanced reinforcement learning algorithms on the Atari-100k benchmark. The code is available at https://github.com/dojeon-ai/hare-tortoise.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Jun 2024.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 10; 2025: 15; 2026: 15.

40 papers.

Sort:

By area:

  1. 2024SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learningcited by 70
  2. 2025Hyperspherical Normalization for Scalable Deep Reinforcement Learningcited by 35
  3. 2024Learning Continually by Spectral Regularizationcited by 34
  4. 2024Streaming Deep Reinforcement Learning Finally Workscited by 24
  5. 2024Plasticity Loss in Deep Reinforcement Learning: A Surveycited by 24
  6. 2024Neuroplastic Expansion in Deep Reinforcement Learningcited by 17
  7. 2024MAD-TD: Model-Augmented Data stabilizes High Update Ratio RLcited by 16
  8. 2024Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RLcited by 14
  9. 2024Plastic Learning with Deep Fourier Featurescited by 14
  10. 2025Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learningcited by 14
  11. 2025Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspectivecited by 14
  12. 2024Self-Normalized Resets for Plasticity in Continual Learningcited by 11
28 more
  1. 2025What Can Grokking Teach Us About Learning Under Nonstationarity?cited by 7
  2. 2026FIRE: Frobenius-Isometry Reinitialization for Balancing the Stability-Plasticity Tradeoffcited by 7
  3. 2025Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Losscited by 6
  4. 2025Reinitializing weights vs units for maintaining plasticity in neural networkscited by 6
  5. 2025Activation Function Design Sustains Plasticity in Continual Learningcited by 6
  6. 2025C3-OWD: A Curriculum Cross-modal Contrastive Learning Framework for Open-World Detectioncited by 5
  7. 2026FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Controlcited by 5
  8. 2024Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learningcited by 4
  9. 2025Plasticity-Aware Mixture of Experts for Learning Under QoE Shifts in Adaptive Video Streamingcited by 4
  10. 2025Overcoming Non-stationary Dynamics with Evidential Proximal Policy Optimizationcited by 2
  11. 2025Sparsity-Driven Plasticity in Multi-Task Reinforcement Learningcited by 2
  12. 2026Do Neural Networks Lose Plasticity in a Gradually Changing World?cited by 2
  13. 2025Silent Neuron Theory and Plasticity Preservation for Deep Reinforcement Learning in Adaptive Video Streamingcited by 1
  14. 2025Preserving Plasticity in Continual Learning with Adaptive Linearity Injectioncited by 1
  15. 2025Recovering Plasticity of Neural Networks via Soft Weight Rescalingcited by 1
  16. 2026Plasticity-Enhanced Multi-Agent Mixture of Experts for Dynamic Objective Adaptation in UAVs-Assisted Emergency Communication Networkscited by 1
  17. 2026C-voting: Confidence-Based Test-Time Voting without Explicit Energy Functionscited by 1
  18. 2026Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement Learningcited by 1
  19. 2026EMAgnet: Parameter-Space EMA Regularization for Policy Gradient Self-Play in Large Gamescited by 1
  20. 2026Can Scale Save Us From Plasticity Loss in Large Language Models?cited by 1
  21. 2025A Simple Baseline for Stable and Plastic Neural Networkscited by 0
  22. 2026CoPeP: Benchmarking Continual Pretraining for Protein Language Modelscited by 0
  23. 2026Rethinking Plasticity in Deep Reinforcement Learningcited by 0
  24. 2026Forager: a lightweight testbed for continual learning with partial observability in RLcited by 0
  25. 2026Adapt or Forget: Provable Tradeoffs Between Adam and SGD in Nonstationary Optimizationcited by 0
  26. 2026Fast and Slow Variational Continual Learningcited by 0
  27. 2026SAOT: Self-Supervised Continual Graph Learning with Structure-Aware Optimal Transportcited by 0
  28. 2026Sustaining Plasticity via Learnable Wavelet Activations in Continual Learningcited by 0