The paper introduces Space-sampled Value Decay (SsVD), a forgetting mechanism designed for non-stationary reinforcement learning where the environment can drift at every timestep. SsVD selectively pulls value estimates of randomly chosen state-space elements toward a baseline, discarding outdated information without requiring reset or change-point detection. Integrated into Soft Actor Critic and Deep Q-Networks, SsVD outperforms its base algorithms across six non-stationary environments and can also promote optimism in hard-exploration tasks.
By Felix St\"orck, Philipp Hartmann, Fabian Hinder, Klaus Neumann, Barbara Hammer
The paper introduces TMLN (Trajectory-Modulatory Landscape Navigation), a method that treats continual learning as an optimal control problem on a curved loss landscape. It uses a diagonal empirical Fisher Information Matrix to approximate a local Riemannian manifold and dynamically modulates a preconditioner based on the network’s historical parameter trajectory. This trajectory‑based preconditioning is integrated into gradient updates to protect important parameter directions without adding explicit penalties, and experiments on class‑ and domain‑incremental benchmarks show a significant reduction in the loss barrier between tasks.
By Isabelle Aguilar, Zayn Andre Zainal, Luis Fernando Herbozo Contreras, Zhaojing Huang, Omid Kavehei
The paper investigates whether enhancing goal representations improves goal-conditioned reinforcement learning (GCRL) performance. By creating an exact temporal-distance goal representation in deterministic mazes and systematically degrading its geometric quality, the authors find that changes in goal representation have little effect on performance. In contrast, degrading the agent’s current state representation more than doubles failure rates, indicating that state representation is the critical bottleneck. The study further demonstrates that simple random Fourier positional encodings can significantly boost performance on challenging navigation tasks without additional map or objective modifications.
By Syed Nazmus Sakib, Abdul Monaf Chowdhury, Nafiul Haque, Shifat E Arman, Md Mehedi Hasan
arXiv:2605. 25170v2 Announce Type: replace-cross Abstract: Training data for olfaction is scattered through disparate, non-standardized datasets that limit the ability to build representative world models.
By Kordel K. France, Ovidiu Daescu
arXiv:2609.17141v1 Announce Type: cross
Abstract: Traversability prediction is a critical component of autonomous navigation in unstructured environments, where complex and uncertain robot-terrain in...
By Hojin Lee, Yunho Lee, Daniel A Duecker, Cheolhyeon Kwon
arXiv:2608. 06276v1 Announce Type: cross Abstract: Persistence diagrams (PDs) provide stable and interpretable summaries of multiscale topological structure.
By Farzana Nasrin