Research
Continual Evolution Strategies in Control Tasks
arXiv:2608.13600v1 Announce Type: cross Abstract: We study Evolution Strategies (ES) for continual control, where agents must adapt to changing tasks without forgetting previous ones. On sequential Mu
arXiv:2608.13600v1 Announce Type: cross Abstract: We study Evolution Strategies (ES) for continual control, where agents must adapt to changing tasks without forgetting previous ones. On sequential MuJoCo locomotion tasks, naive ES suffers from severe catastrophic forgetting. Replay substantially improves retention and can induce positive transfer, while larger replay budgets reduce plasticity. Overall, these results show that ES can support continual adaptation in control and that replay is an effective mechanism for mitigating forgetting.
Related
- Dynamic Mixture of Latent Memories for Self-Evolving Agents
- From Order to Distribution: A Spectral Characterization of Forgetting in Continual Learning
- Adaptive Estimation and Optimal Control in Offline Contextual MDPs without Stationarity
Source: arXiv cs.LG | 2026-08-17