arXiv:2606. 06227v1 Announce Type: cross Abstract: A reinforcement-learning agent maximises its reward, which can diverge from the outcome its designer intended.
arXiv:2606. 06227v2 Announce Type: replace-cross Abstract: A reinforcement-learning agent maximises its reward, which can diverge from the outcome its designer intended.
arXiv:2607. 12626v1 Announce Type: cross Abstract: Closed-loop wall control learnt by multi-agent reinforcement learning can lower skin-friction drag in turbulent channels, but these gradient-based policies are trained on small periodic boxes and exhibit reduced performance when carried over to a larger domain.
Closed-loop wall control learnt by multi-agent reinforcement learning can lower skin-friction drag in turbulent channels, but these gradient-based policies are trained on small periodic boxes and exhibit reduced performance when carried over to a larger domain. We recently showed that such policies are also prone to saturated bang-bang actuations that collapse into standing streamwise waves whose scale is set by the computational box rather than by the near-wall cycle, and proposed architectural fixes that avoid these degeneracies.
arXiv:2606. 00949v1 Announce Type: cross Abstract: We propose a method combining Multi-Agent Deep Reinforcement Learning (MARL) and eXplainable Deep Learning (XDL) to reduce drag in wall-bounded turbulent flows.
arXiv:2608. 02508v1 Announce Type: new Abstract: Learning-based memory systems for self-evolving LLM agents face two tightly coupled challenges.
arXiv:2512.08463v2 Announce Type: replace Abstract: We study how privileged information about a physical system affects the discovery of high-performing policies when training a reinforcement learnin...
arXiv:2608. 07228v1 Announce Type: new Abstract: When a reinforcement learning agent cannot observe the full state, we usually blame its policies: it cannot see enough to represent a good one.
The paper investigates the problem of sharing a single critic across multiple parallel environments in reinforcement learning. It shows that when environments assign different expected returns to the same state, a shared critic must reconcile conflicting value targets, which can distort advantage estimates and misguide policy updates. The authors propose a simple fix—providing the critic with the environment index—demonstrating through bandit models and experiments on CartPole, MuJoCo, BipedalWalker, and 16 Procgen games that this conditional critic stabilizes learning and boosts returns, achieving a 40.8% improvement in aggregate normalized return on unseen levels.
arXiv:2606. 08602v1 Announce Type: cross Abstract: We present an online reinforcement learning (RL) algorithm for fine-tuning flow-matching policies in continuous-control problems.
arXiv:2605. 03065v2 Announce Type: replace Abstract: Generative control policies (GCPs), such as diffusion- and flow-based control policies, have emerged as effective parameterizations for robot learning.
arXiv:2606. 11891v1 Announce Type: cross Abstract: Multi-objective reinforcement learning for humanoid robots must coordinate locomotion and manipulation within a single policy.
arXiv:2607. 11565v1 Announce Type: cross Abstract: Active flow control involves nonlinear dynamics, partial observations, and computationally expensive simulations, making controller design particularly challenging.