arXivTristan Shah, Wooyoung Chung, Volodomyr Makarenko, Juan Wachs, Stas TiomkinThu, Oct 1, 2026, 9:38 AM PDT
score 16.4
Robots Learn to Move Without Hand-Crafted Rewards
Original: Bellman Meets Lyapunov: Unsupervised Reinforcement Learning via Mastering Chaos
Source: arxiv.org ↗
Writing ELI5 summary…