arXiv:2607. 14001v1 Announce Type: new Abstract: We suggest using the Lyapunov characteristic exponent (LCE) as a dense reward signal for the reinforcement learning problem of stabilizing the inverted pendulum with vertical motion.
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.
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.
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.
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.
arXiv:2602. 04132v4 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) has achieved remarkable success in solving complex sequential decision-making problems.
The paper introduces a framework for combining large language models (LLMs) with reinforcement learning (RL) by treating the LLM as a planner and the RL agent as a controller. It formalizes this hybrid setup as a Goal-Augmented Markov Decision Process and proves that using the LLM’s per‑state progress score as a bounded potential function preserves the optimal policy set, even if the LLM scores are inaccurate. The authors validate their theoretical result with numerical experiments on a small MDP, testing four potential configurations, including an adversarial case with a potential scaled twenty times the base reward.
arXiv:2607. 18365v1 Announce Type: cross Abstract: Reinforcement learning (RL) for legged robots is advancing locomotion, demonstrating its ability to adapt to new and challenging terrain.
The article "Dynamical System Transfer Learning with Reduced Order Models" discusses how to enhance reinforcement learning for complex physics problems by employing reduced order models. It explores the application of transfer learning techniques to dynamical systems, aiming to improve the efficiency and effectiveness of reinforcement learning algorithms in physics-based simulations.
arXiv:2609.05650v1 Announce Type: new Abstract: We propose a reinforcement learning framework in which exploration is driven by intrinsic curiosity, designed for scenarios where environments are non-...
The paper discusses how reinforcement learning theory relies on probability theory via Markov chains and highlights a deep link between probability theory and potential theory. It reviews this connection and examines how a potential-theoretic perspective can be applied to core RL representations and algorithms under a fixed‑policy assumption, suggesting possible gains in sample efficiency and formal constraints. The authors also note that relaxing the fixed‑policy assumption allows the linear potential theory framework to extend naturally to nonlinear cases.
arXiv:2410. 11894v3 Announce Type: replace-cross Abstract: Dynamical systems form the foundation of scientific discovery, traditionally modeled with predefined state variables such as the angle and angular velocity, and differential equations such as the equation of motion for a single pendulum.