The paper introduces Patterns of Past Rewards (PPR), a lightweight, algorithm‑agnostic online change‑point detector for cooperative multi‑agent reinforcement learning. PPR smooths agents’ return streams, highlights recent changes, and applies a statistical drift detector to flag significant shifts. Experiments in a custom Speaker‑Listener environment show that PPR balances detection speed and alarm stability, outperforming both a smoothed‑return baseline and a raw‑return detector.
arXiv:2607. 08373v1 Announce Type: cross Abstract: Connected vehicles are autonomous cyber-physical systems whose behavior must be continuously monitored during operation to detect deviations from normal operation before they propagate into failures.
arXiv:2604.22785v2 Announce Type: replace Abstract: We develop a unified treatment of credit assignment for RL training in multi-agent LLM systems. We show that observed reward alone cannot distingui...
arXiv:2605. 12655v2 Announce Type: replace Abstract: Multi-agent reinforcement learning (MARL) in real-world use cases may need to adapt to external natural language instructions that interrupt ongoing behavior and conflict with long-horizon objectives.
arXiv:2607. 17914v1 Announce Type: cross Abstract: Robust multi-agent coordination relies heavily on inter-agent communication, which is frequently disrupted by physical and environmental constraints in real-world deployments.
Reliable reinforcement learning (RL) agents must maintain operational integrity amidst sensor malfunctions, dynamic disturbances, and slow environmental shifts. The detection of out-of-distribution conditions is pivotal to determining when an agent's observations, transitions, or trajectory dynamics deviate from the assumptions underpinning its policy training.
arXiv:2602. 11406v2 Announce Type: replace-cross Abstract: We consider an online learning problem in environments with multiple change points.
arXiv:2506. 14990v3 Announce Type: replace Abstract: Benchmarks play a central role in reinforcement learning (RL) research, yet their computational constraints often shape what is studied.
Early Classification of Time Series (ECTS) requires making accurate decisions as early as possible in inherently online and evolving environments. Yet, most existing methods assume stationarity and rely on separable designs, where classification and triggering are optimized independently, an assumption that fundamentally limits their adaptability under drift.
arXiv:2608. 20044v1 Announce Type: new Abstract: Early Classification of Time Series (ECTS) requires making accurate decisions as early as possible in inherently online and evolving environments.
arXiv:2606. 29126v1 Announce Type: new Abstract: Cooperative multi-agent reinforcement learning (MARL) often relies on communication to mitigate partial observability, yet most existing protocols treat messages as flat dense vectors detached from the structure of the observations they summarize.
arXiv:2607. 12523v1 Announce Type: cross Abstract: Reliable reinforcement learning (RL) agents must maintain operational integrity amidst sensor malfunctions, dynamic disturbances, and slow environmental shifts.
arXiv:2606. 17477v1 Announce Type: cross Abstract: Out-of-distribution (OOD) detection in dynamic open-world environments requires a model to continually adapt to evolving data distributions while generalizing to covariate-shifted inputs and rejecting semantic-shifted OOD examples.