Paper: arxiv.org/abs/2605.26357
Blog: rayofsunshine.me/projects/bal...
Code:
MuJoCo / PyTorch: github.com/raymondchua/...
Four Rooms / Jax: github.com/raymondchua/...
Looking forward to discussions at ICML 2026 in Seoul 🇰🇷
15/15
A hallmark of intelligence is the ability to adapt in non-stationary environments, yet deep Reinforcement Learning (RL) agents often struggle in such settings. Prior studies introduce non-stationarity...