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

DGX agentpaper
researcharxiv-cs-lg

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

Source: arXiv cs.LG | 2026-08-17

Loading related sources…