TL;DR
F orecasting in Non-stationary O ffline RL (F ORL), a framework that combines zero-shot forecasting with the agent’s experience, aims to bridge the gap between offline RL and the complexities of real-world, non-stationary environments.
This work leverages the next-state variable as a natural proxy for the unobserved action and proposes an influence-function-based estimator called LURE (Learning from the Unseen: Robust Estimator), which is multiply robust, remaining consistent under several combinations of correctly specified nuisance components, and...
Robust reinforcement learning (RRL) aims to develop a robust policy that maintains stable performance across diverse environments characterized by an uncertainty set. This set consists of perturbed environments derived from a nominal (training) environment that generates samples, thereby capturing potential discrepanci...
This paper presents the first application of calibration models trained on offline data to approximate environment dynamics and enable offline hyperparameter selection in a real-world industrial setting: a municipal water treatment plant.
Experiments on partially observable single-agent and cooperative multi-agent tasks show that RNN-ProVe yields more quantitative, feasibility-aware probabilistic guarantees than existing tools, while scaling to recurrent and multi-agent settings.
This work presents OOD-RL-Bench, a comprehensive and extensible framework designed to evaluate OOD detectors against categories of anomalies injected into RL trajectories, and makes the framework, trained policy checkpoint, and complete results publicly available as a reproducible artefact.
ITRM is proposed, a novel approach to anomaly detection in visual reinforcement learning that is fully agent-agnostic and does not require access to policy internals, based on the observation that deviations from nominal environment dynamics can be identified through discrepancies in the latent representations of a lea...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
