Bellman Meets Lyapunov: Unsupervised Reinforcement Learning via Mastering Chaos

Excerpt

arXiv:2610.02012v1 Announce Type: new Abstract: Reinforcement learning (RL) is a powerful paradigm for training agents, yet its success rests on domain expertise of human engineers who design informative reward signals for every new task. Unsupervised RL aims to reduce this engineering with intrinsic motivation (IM): reward signals that emerge from the agent environment interaction itself. Existing IM objectives, however, involve the selection of information variables, which re-introduces domain