The paper introduces a data‑driven control framework that uses surrogate modeling and reinforcement learning to optimize target polarization in nuclear physics scattering experiments. By training Gaussian process and multilayer perceptron models on operational data from the APOLLO cryogenic target system, the authors demonstrate that Gaussian processes provide calibrated uncertainty estimates and better handle distributional shifts. Embedding the surrogate model in a simulation environment, a reinforcement learning agent trained with a lower‑confidence‑bound reward achieves nearly a 2× improvement over manual operator tuning.
arXiv:2609.08620v1 Announce Type: cross Abstract: We address the challenge of scalable uncertainty quantification in large-scale scientific applications, where complex state-of-the-art machine learni...
arXiv:2604.19146v2 Announce Type: replace Abstract: Particle accelerator beamline optimization is a high-dimensional control problem traditionally requiring significant expert intervention. We presen...
Effective model-based reinforcement learning in stochastic environments requires planning that accounts for predictive uncertainty. Propagating full state distributions analytically offers a principled way to do this, but has traditionally required restrictive policy or reward structures to remain tractable.
The paper introduces PSPO, a method for offline policy optimization that treats the dynamics model as a random variable, enabling controlled exploration of out‑of‑distribution (OOD) regions while maintaining robustness. By alternating updates of the posterior distribution and the policy, PSPO achieves a regularized optimization algorithm with convergence guarantees. Experiments on standard benchmarks show that PSPO outperforms state‑of‑the‑art baselines and retains a pessimism‑free property without sacrificing robustness.
arXiv:2606. 31291v1 Announce Type: new Abstract: Deep reinforcement learning has the potential to solve attitude control problems more adaptively, precisely, and robustly by handling nonlinear dynamics, uncertainties, and failure cases more effectively than traditional attitude control approaches.
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.
arXiv:2608. 02519v1 Announce Type: new Abstract: Effective model-based reinforcement learning in stochastic environments requires planning that accounts for predictive uncertainty.
The paper explores how to use gradients of simulator outputs with respect to input parameters to improve Bayesian inference for expensive simulators. By incorporating gradient information into Gaussian process surrogate models, the authors show that Bayesian optimization can converge faster under a limited simulation budget. They find that reverse‑mode differentiation yields efficiency gains, while forward‑mode does not offset its computational cost, especially when the number of parameters exceeds the output dimensionality.
arXiv:2610.19783v1 Announce Type: new Abstract: Reinforcement learning (RL) holds the promise of learning a policy that can outperform what is shown in the data. However, in practice, such systems su...
arXiv:2607. 23404v1 Announce Type: new Abstract: Self-driving laboratories increasingly rely on multi-fidelity Bayesian optimization (MFBO) to balance cheap, approximate evaluations against scarce, expensive ones, with a predictive surrogate at its core.
The paper introduces Diffusion-Augmented Markov Decision Processes (DA‑MDPs), a framework that extends Maximum Entropy Reinforcement Learning to diffusion-based policies. DA‑MDPs treat each reverse‑diffusion step as an RL decision, deriving a tractable reverse‑KL bound that decomposes across denoising transitions and yields diffusion‑augmented soft rewards, value functions, and policy objectives. The authors implement this framework with PPO, REPPO, and a maximum‑entropy WPO variant, showing improved continuous‑control performance, higher success rates on manipulation tasks, and memory‑efficient training with action chunking.
arXiv:2606. 25197v1 Announce Type: new Abstract: Learning effective policies for adaptive data acquisition remains challenging: posterior-based methods rely on surrogate models and posterior approximations that can be misspecified or biased, while direct policy-learning methods map from historical observations and fail to exploit available model representations, making learning harder.