arXiv Machine Learning

Optimistic Online LQR via Intrinsic Rewards

The paper introduces IR‑LQR, an optimistic online linear quadratic regulator that incorporates intrinsic rewards and variance regularization to encourage exploration while maintaining the standard LQR structure. By only adjusting the cost function, IR‑LQR remains computationally simple yet achieves the optimal worst‑case regret rate of √T. The authors validate the method with numerical experiments on aircraft pitch angle control and a UAV example, comparing it to state‑of‑the‑art online LQR algorithms.

arXiv Machine Learning
Aug 24

Smart Exploration in Reinforcement Learning using Bounded Uncertainty Models

The paper introduces BUMEX, a reinforcement learning exploration strategy that leverages a set of prior models containing the true transition kernel and reward function. By optimizing over this model set, the method derives upper and lower bounds on the Q‑function to guide exploration, providing theoretical guarantees of convergence to the optimal policy. When the model set follows a bounded‑parameter MDP structure, the optimization becomes convex, enabling finite‑time convergence under mild assumptions and demonstrating accelerated learning in simulations.

By J. S. van Hulst, W. P. M. H. Heemels, D. J. Antunes
arXiv AI
Jun 30

Exploration and Online Transfer with Behavioral Foundation Models

arXiv:2606. 29980v1 Announce Type: new Abstract: Zero-shot Transfer in Reinforcement Learning (RL) aims to train an agent that can generate optimal policies for any reward function, without additional learning at transfer time, while training only on reward-free trajectories.

By Louis Bagot (SyCoSMA), Mathieu Lefort (LIRIS, SyCoSMA, IRISA, MALT, UR), La\"etitia Matignon (SyCoSMA)
arXiv AI
Jun 29

Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking

arXiv:2604. 26360v2 Announce Type: replace-cross Abstract: Reinforcement learning from human feedback (RLHF) systems face a compounding alignment challenge: not only are learned reward models uncertain about unseen state-action pairs, but the human preference annotations they are trained on are themselves inconsistent, context-dependent, and noisy.

By Disha Singha
arXiv Machine Learning
Jun 5

Exploration via linearly perturbed loss minimisation

arXiv:2311. 07565v3 Announce Type: replace Abstract: We introduce exploration via linear loss perturbations (EVILL), a randomised exploration method for structured stochastic bandit problems that works by solving for the minimiser of a linearly perturbed regularised negative log-likelihood function.

By David Janz, Shuai Liu, Alex Ayoub, Csaba Szepesv\'ari
arXiv Machine Learning
3d ago

Accelerating Reinforcement Learning via MPC Solver-Gradient Guidance for Weights-varying MPC

The paper introduces Solver-Gradient Guided Reinforcement Learning (SG‑RL), a method that augments standard RL with bounded gradients from a differentiable MPC solver to adapt cost‑function weights online. SG‑RL integrates solver‑gradient guidance into PPO through actor‑update scaling, policy loss, advantage estimation, and value‑function learning, achieving comparable or superior closed‑loop performance while requiring up to 70.6% fewer samples. Experiments on two autonomous racing platforms with intentional model mismatch demonstrate that SG‑RL outperforms both RL and gradient‑based policy learning baselines and generalizes zero‑shot to unseen environments.

By Baha Zarrouki, Arslan Thobani, Jasper Hoffmann, Mattia Piccinini, Rudolf Reiter, Felix Jahncke, S\'ebastien Gros, Davide Scaramuzza, Johannes Betz