# Diagnose, Recover, Certify: Task Readiness under Hidden Dynamics Changes

arXiv: https://arxiv.org/abs/2609.20304 · HTML: https://mlsanity.com/paper/2609.20304/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 18 references that are in the map.
- First posted on arXiv 30 Jul 2026.

## Builds on (most cited first, 11 of 11)

- [Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables](https://mlsanity.com/paper/1903.08254/) (2019)
- [Safe Model-based Reinforcement Learning with Stability Guarantees](https://mlsanity.com/paper/1705.08551/) (2017)
- [SelectiveNet: A Deep Neural Network with an Integrated Reject Option](https://mlsanity.com/paper/1901.09192/) (2019)
- [Safe Policy Improvement with Baseline Bootstrapping](https://mlsanity.com/paper/1712.06924/) (2017)
- [Optimistic Active Exploration of Dynamical Systems](https://mlsanity.com/paper/2306.12371/) (2023)
- [Factored Adaptation for Non-Stationary Reinforcement Learning](https://mlsanity.com/paper/2203.16582/) (2022)
- [ASID: Active Exploration for System Identification in Robotic Manipulation](https://mlsanity.com/paper/2404.12308/) (2024)
- [Distributionally Robust Off-Dynamics Reinforcement Learning: Provable Efficiency with Linear Function Approximation](https://mlsanity.com/paper/2402.15399/) (2024)
- [ODRL: A Benchmark for Off-Dynamics Reinforcement Learning](https://mlsanity.com/paper/2410.20750/) (2024)
- [Bandit Quickest Changepoint Detection](https://mlsanity.com/paper/2107.10492/) (2021)
- [A Behavior-Aware Approach for Deep Reinforcement Learning in Non-stationary Environments without Known Change Points](https://mlsanity.com/paper/2405.14214/) (2024)

## Abstract (arXiv)

A deployed control policy can conceal consequential dynamics changes: an actuator may lose effectiveness without affecting the current task when the policy rarely excites it, despite being critical for a future task that has not yet been specified. We introduce task readiness under dormant dynamics drift, a decision problem that unifies active change diagnosis and post-change control recovery under a limited, task-agnostic interaction budget. An agent must identify whether and where local dynamics have changed, use a small number of informative interactions to characterize the change before downstream task identity is revealed, and subsequently provide each candidate task with either a recovered policy and a calibrated lower bound on its achievable return or an abstention decision to a safe fallback. We propose Evidence-Gated Matched-Pulse Transport, an intervention-based Bayesian procedure that couples fault localization with estimation of actuator effectiveness through a shared matched-response representation, thereby preserving diagnostic reliability while converting localized evidence into recovery-relevant uncertainty. This uncertainty is propagated to task-conditioned policy selection and readiness certification, enabling deployment decisions that explicitly trade off expected performance, confidence, and fallback use. We evaluate the resulting framework on a diverse suite of dormant-actuator benchmarks spanning multiple simulators, under a protocol that separates diagnosis from capability recovery, scores deployment by readiness coverage, selective risk, and interaction cost as well as return, and identifies the fault regimes in which transported evidence is decisive.