arXiv Machine Learning
On Policy Stochasticity in Mutual Information Optimal Control of Linear Systems
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Sep 2
Provably Efficient Federated Reinforcement Learning with Linear Function Approximation and Logarithmic Communication Cost
The paper introduces Fed‑LSVI, a federated online reinforcement learning algorithm that uses linear function approximation in episodic Markov decision processes. It achieves a regret bound of ≥O(√{Md^3H^4T}) while only exchanging compressed sufficient statistics, thereby meeting privacy constraints. The method reduces communication cost to logarithmic in the number of episodes, a marked improvement over previous approaches that required linear communication.
arXiv Machine Learning
Jul 21
When Can Safe Controllers Adapt? Information before Commitment
arXiv:2607. 16895v1 Announce Type: new Abstract: Safe adaptive control is online adaptation under a safety guarantee on the learning trajectory itself.
arXiv Machine Learning
Aug 4
Learning-Based Stochastic Optimal Control with Infinite-Horizon Probabilistic Constraints
arXiv:2608. 01151v1 Announce Type: cross Abstract: In this paper, we consider stochastic optimal control problems with infinite-horizon joint chance constraints.
arXiv Machine Learning
Aug 10
Wasserstein Policy Gradient for Entropy-Regularized Linear-Quadratic Control
arXiv:2608. 07433v1 Announce Type: cross Abstract: Wasserstein policy gradient (WPG) updates state-conditional action laws by transport in the action space.
arXiv Machine Learning
Sep 14
Linear Exponential Quadratic Gaussian Covariance Steering
The paper formulates and analyzes the linear exponential quadratic Gaussian (LEQG) covariance steering problem in continuous time over a finite horizon. It shows that the optimal controller, still a linear state feedback, cannot be expressed in closed form but is parameterized by a symmetric matrix solving an algebraic equation that captures the risk‑sensitivity parameter. The authors demonstrate that this controller generalizes the risk‑neutral case and prove existence‑uniqueness of solutions near the known risk‑neutral solution for matched noise and input channels, illustrated with a numerical example.
arXiv AI
Jul 15
Calculating Mutual Information between a Reward Maximizer and its Environment
arXiv:2602. 12963v2 Announce Type: replace Abstract: An important question in the field of AI is the extent to which successful behaviour requires an internal representation of the world.