Studying strong controllers that work throughout many partially observable environments

In clever programs, functions vary from autonomous robotics to predictive upkeep issues. To manage these programs, the important elements are captured with a mannequin. Once we design controllers for these fashions, we virtually at all times face the identical problem: uncertainty. We’re hardly ever in a position to see the entire image. Sensors are noisy, fashions of the system are imperfect; the world by no means behaves precisely as anticipated.

Think about a robotic navigating round an impediment to achieve a “aim” location. We summary this state of affairs right into a grid-like surroundings. A rock might block the trail, however the robotic doesn’t know precisely the place the rock is. If it did, the issue could be fairly straightforward: plan a route round it. However with uncertainty concerning the impediment’s place, the robotic should study to function safely and effectively regardless of the place the rock seems to be.

This easy story captures a wider problem: designing controllers that may deal with each partial observability and mannequin uncertainty. On this weblog submit, I’ll information you thru our IJCAI 2025 paper, “Strong Finite-Reminiscence Coverage Gradients for Hidden-Mannequin POMDPs”, the place we discover designing controllers that carry out reliably even when the surroundings will not be exactly recognized.

When you may’t see every little thing

When an agent doesn’t totally observe the state, we describe its sequential decision-making downside utilizing a partially observable Markov choice course of (POMDP). POMDPs mannequin conditions through which an agent should act, primarily based on its coverage, with out full data of the underlying state of the system. As an alternative, it receives observations that present restricted details about the underlying state. To deal with that ambiguity and make higher selections, the agent wants some type of reminiscence in its coverage to recollect what it has seen earlier than. We sometimes characterize such reminiscence utilizing finite-state controllers (FSCs). In distinction to neural networks, these are sensible and environment friendly coverage representations that encode inner reminiscence states that the agent updates because it acts and observes.

From partial observability to hidden fashions

Many conditions hardly ever match a single mannequin of the system. POMDPs seize uncertainty in observations and within the outcomes of actions, however not within the mannequin itself. Regardless of their generality, POMDPs can’t seize units of partially observable environments. In actuality, there could also be many believable variations, as there are at all times unknowns — completely different impediment positions, barely completely different dynamics, or various sensor noise. A controller for a POMDP doesn’t generalize to perturbations of the mannequin. In our instance, the rock’s location is unknown, however we nonetheless need a controller that works throughout all attainable places. This can be a extra practical, but in addition a more difficult state of affairs.

To seize this mannequin uncertainty, we launched the hidden-model POMDP (HM-POMDP). Somewhat than describing a single surroundings, an HM-POMDP represents a set of attainable POMDPs that share the identical construction however differ of their dynamics or rewards. An essential reality is {that a} controller for one mannequin can be relevant to the opposite fashions within the set.

The true surroundings through which the agent will finally function is “hidden” on this set. This implies the agent should study a controller that performs effectively throughout all attainable environments. The problem is that the agent doesn’t simply need to motive about what it might’t see but in addition about which surroundings it’s working in.

A controller for an HM-POMDP should be strong: it ought to carry out effectively throughout all attainable environments. We measure the robustness of a controller by its strong efficiency: the worst-case efficiency over all fashions, offering a assured decrease certain on the agent’s efficiency within the true mannequin. If a controller performs effectively even within the worst case, we might be assured it should carry out acceptably on any mannequin of the set when deployed.

In direction of studying strong controllers

So, how will we design such controllers?

We developed the strong finite-memory coverage gradient rfPG algorithm, an iterative strategy that alternates between the next two key steps:

• Strong coverage analysis: Discover the worst case. Decide the surroundings within the set the place the present controller performs the worst.
• Coverage optimization: Enhance the controller for the worst case. Modify the controller’s parameters with gradients from the present worst-case surroundings to enhance strong efficiency.

Over time, the controller learns strong habits: what to recollect and tips on how to act throughout the encountered environments. The iterative nature of this strategy is rooted within the mathematical framework of “subgradients”. We apply these gradient-based updates, additionally utilized in reinforcement studying, to enhance the controller’s strong efficiency. Whereas the small print are technical, the instinct is straightforward: iteratively optimizing the controller for the worst-case fashions improves its strong efficiency throughout all of the environments.

Underneath the hood, rfPG makes use of formal verification methods applied within the device PAYNT, exploiting structural similarities to characterize giant units of fashions and consider controllers throughout them. Thanks to those developments, our strategy scales to HM-POMDPs with many environments. In observe, this implies we will motive over greater than 100 thousand fashions.

What’s the influence?

We examined rfPG on HM-POMDPs that simulated environments with uncertainty. For instance, navigation issues the place obstacles or sensor errors diversified between fashions. In these assessments, rfPG produced insurance policies that weren’t solely extra strong to those variations but in addition generalized higher to fully unseen environments than a number of POMDP baselines. In observe, that suggests we will render controllers strong to minor variations of the mannequin. Recall our working instance, with a robotic that navigates a grid-world the place the rock’s location is unknown. Excitingly, rfPG solves it near-optimally with solely two reminiscence nodes! You may see the controller beneath.

By integrating model-based reasoning with learning-based strategies, we develop algorithms for programs that account for uncertainty quite than ignore it. Whereas the outcomes are promising, they arrive from simulated domains with discrete areas; real-world deployment would require dealing with the continual nature of varied issues. Nonetheless, it’s virtually related for high-level decision-making and reliable by design. Sooner or later, we’ll scale up — for instance, by utilizing neural networks — and intention to deal with broader lessons of variations within the mannequin, akin to distributions over the unknowns.

Need to know extra?

Thanks for studying! I hope you discovered it attention-grabbing and received a way of our work. You will discover out extra about my work on marisgg.github.io and about our analysis group at ai-fm.org.

This weblog submit relies on the next IJCAI 2025 paper:

• Maris F. L. Galesloot, Roman Andriushchenko, Milan Češka, Sebastian Junges, and Nils Jansen: “Strong Finite-Reminiscence Coverage Gradients for Hidden-Mannequin POMDPs”. In IJCAI 2025, pages 8518–8526.

For extra on the methods we used from the device PAYNT and, extra typically, about utilizing these methods to compute FSCs, see the paper beneath:

• Roman Andriushchenko, Milan Češka, Filip Macák, Sebastian Junges, Joost-Pieter Katoen: “An Oracle-Guided Strategy to Constrained Coverage Synthesis Underneath Uncertainty”. In JAIR, 2025.

Should you’d wish to study extra about one other method of dealing with mannequin uncertainty, take a look at our different papers as effectively. As an illustration, in our ECAI 2025 paper, we design strong controllers utilizing recurrent neural networks (RNNs):

• Maris F. L. Galesloot, Marnix Suilen, Thiago D. Simão, Steven Carr, Matthijs T. J. Spaan, Ufuk Topcu, and Nils Jansen: “Pessimistic Iterative Planning with RNNs for Strong POMDPs”. In ECAI, 2025.

And in our NeurIPS 2025 paper, we examine the analysis of insurance policies:

• Merlijn Krale, Eline M. Bovy, Maris F. L. Galesloot, Thiago D. Simão, and Nils Jansen: “On Evaluating Insurance policies for Strong POMDPs”. In NeurIPS, 2025.

---