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

arXiv: https://arxiv.org/abs/2406.02596 · HTML: https://mlsanity.com/paper/2406.02596/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jun 2024.

## Built on by (most cited first, 30 of 43)

- [SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning](https://mlsanity.com/paper/2410.09754/) (2024)
- [Hyperspherical Normalization for Scalable Deep Reinforcement Learning](https://mlsanity.com/paper/2502.15280/) (2025)
- [Learning Continually by Spectral Regularization](https://mlsanity.com/paper/2406.06811/) (2024)
- [Streaming Deep Reinforcement Learning Finally Works](https://mlsanity.com/paper/2410.14606/) (2024)
- [Plasticity Loss in Deep Reinforcement Learning: A Survey](https://mlsanity.com/paper/2411.04832/) (2024)
- [Neuroplastic Expansion in Deep Reinforcement Learning](https://mlsanity.com/paper/2410.07994/) (2024)
- [MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL](https://mlsanity.com/paper/2410.08896/) (2024)
- [Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL](https://mlsanity.com/paper/2410.01930/) (2024)
- [Plastic Learning with Deep Fourier Features](https://mlsanity.com/paper/2410.20634/) (2024)
- [Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning](https://mlsanity.com/paper/2505.24061/) (2025)
- [Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective](https://mlsanity.com/paper/2506.03951/) (2025)
- [Self-Normalized Resets for Plasticity in Continual Learning](https://mlsanity.com/paper/2410.20098/) (2024)
- [What Can Grokking Teach Us About Learning Under Nonstationarity?](https://mlsanity.com/paper/2507.20057/) (2025)
- [FIRE: Frobenius-Isometry Reinitialization for Balancing the Stability-Plasticity Tradeoff](https://mlsanity.com/paper/2602.08040/) (2026)
- [Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss](https://mlsanity.com/paper/2502.01342/) (2025)
- [Reinitializing weights vs units for maintaining plasticity in neural networks](https://mlsanity.com/paper/2508.00212/) (2025)
- [Activation Function Design Sustains Plasticity in Continual Learning](https://mlsanity.com/paper/2509.22562/) (2025)
- [C3-OWD: A Curriculum Cross-modal Contrastive Learning Framework for Open-World Detection](https://mlsanity.com/paper/2509.23316/) (2025)
- [FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control](https://mlsanity.com/paper/2604.04539/) (2026)
- [Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning](https://mlsanity.com/paper/2406.06037/) (2024)
- [Plasticity-Aware Mixture of Experts for Learning Under QoE Shifts in Adaptive Video Streaming](https://mlsanity.com/paper/2504.09906/) (2025)
- [Overcoming Non-stationary Dynamics with Evidential Proximal Policy Optimization](https://mlsanity.com/paper/2503.01468/) (2025)
- [Preserving Plasticity in Continual Learning with Adaptive Linearity Injection](https://mlsanity.com/paper/2505.09486/) (2025)
- [Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning](https://mlsanity.com/paper/2508.06871/) (2025)
- [Do Neural Networks Lose Plasticity in a Gradually Changing World?](https://mlsanity.com/paper/2602.09234/) (2026)
- [Silent Neuron Theory and Plasticity Preservation for Deep Reinforcement Learning in Adaptive Video Streaming](https://mlsanity.com/paper/2505.01584/) (2025)
- [Recovering Plasticity of Neural Networks via Soft Weight Rescaling](https://mlsanity.com/paper/2507.04683/) (2025)
- [Plasticity-Enhanced Multi-Agent Mixture of Experts for Dynamic Objective Adaptation in UAVs-Assisted Emergency Communication Networks](https://mlsanity.com/paper/2604.09028/) (2026)
- [C-voting: Confidence-Based Test-Time Voting without Explicit Energy Functions](https://mlsanity.com/paper/2604.13521/) (2026)
- [Adapt or Forget: Provable Tradeoffs Between Adam and SGD in Nonstationary Optimization](https://mlsanity.com/paper/2605.04269/) (2026)

## 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.