arXiv:2606. 27112v1 Announce Type: cross Abstract: This paper proposes a corrected heavy-ball Q-learning method for reinforcement learning (RL) and establishes its convergence.
By Donghwan Lee
The paper introduces Forward CIP (F‑CIP), an RL‑native formulation of the Controllable Information Production objective that relies solely on system dynamics, eliminating the need for domain‑specific information variable selection. F‑CIP is proven compatible with reinforcement learning and, when applied to existing algorithms, enables agents to autonomously discover primitive behaviors such as balancing and maintaining controllability. Coupled with a simple forward‑velocity reward, the method yields coordinated gaits like hopping and running without reward engineering.
By Tristan Shah, Wooyoung Chung, Volodomyr Makarenko, Juan Wachs, Stas Tiomkin
This paper proposes a corrected heavy-ball Q-learning method for reinforcement learning (RL) and establishes its convergence. It also identifies conditions under which the method is theoretically guaranteed to converge faster than standard Q-learning.
arXiv:2608. 02433v1 Announce Type: new Abstract: Reinforcement learning and control theory are two adjacent scientific fields that focus on optimizing the controller of unknown dynamical systems using feedback.
By Claire Vernade, Onno Eberhard, Martha White, Florian D\"orfler, Csaba Szepesv\'ari, Miroslav Krstic, Michael Muehlebach
The paper introduces a Hessian‑based, integrator‑free method for numerically continuing periodic orbits in dynamical systems, using a Fourier series representation and automatic differentiation to avoid hand‑derived Jacobians. By exploiting flat directions in the loss landscape, the approach efficiently guides the search for periodic orbits, accurately initializes oscillations around unstable fixed points, and detects orbit family intersections and subharmonic bifurcations. Demonstrated on the double pendulum, the method produces full continuations from fixed points, revealing bifurcations along orbit families and identifying previously undocumented periodic orbits where both pendulum masses are never simultaneously at rest.
By Leo Yao, Ziming Liu, Max Tegmark
arXiv:2602. 04132v4 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) has achieved remarkable success in solving complex sequential decision-making problems.
By Dhruv S. Kushwaha, Zoleikha A. Biron