# Act-Then-Measure: Reinforcement Learning for Partially Observable Environments with Active Measuring

arXiv: https://arxiv.org/abs/2303.08271 · HTML: https://mlsanity.com/paper/2303.08271/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 29 references that are in the map.
- First posted on arXiv 14 Mar 2023.

## Builds on (most cited first, 13 of 13)

- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [When to Trust Your Model: Model-Based Policy Optimization](https://mlsanity.com/paper/1906.08253/) (2019)
- [Reinforcement Learning in Healthcare: A Survey](https://mlsanity.com/paper/1908.08796/) (2019)
- [Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds](https://mlsanity.com/paper/1901.00210/) (2019)
- [Collapsing Bandits and Their Application to Public Health Interventions](https://mlsanity.com/paper/2007.04432/) (2020)
- [A PAC RL Algorithm for Episodic POMDPs](https://mlsanity.com/paper/1605.08062/) (2016)
- [Deep Reinforcement Learning for Autonomous Internet of Things: Model, Applications and Challenges](https://mlsanity.com/paper/1907.09059/) (2019)
- [Model-Based Bayesian Exploration](https://mlsanity.com/paper/1301.6690/) (2013)
- [Reinforcement Learning with Efficient Active Feature Acquisition](https://mlsanity.com/paper/2011.00825/) (2020)
- [Active Measure Reinforcement Learning for Observation Cost Minimization](https://mlsanity.com/paper/2005.12697/) (2020)
- [Safe Policy Improvement for POMDPs via Finite-State Controllers](https://mlsanity.com/paper/2301.04939/) (2023)
- [Improving Automated Driving through POMDP Planning with Human Internal States](https://mlsanity.com/paper/2005.14549/) (2020)
- [Online Active Perception for Partially Observable Markov Decision Processes with Limited Budget](https://mlsanity.com/paper/1910.02130/) (2019)

## Built on by (most cited first, 10 of 10)

- [When to Sense and Control? A Time-adaptive Approach for Continuous-Time RL](https://mlsanity.com/paper/2406.01163/) (2024)
- [Beyond Sliding Windows: Learning to Manage Memory in Non-Markovian Environments](https://mlsanity.com/paper/2512.19154/) (2025)
- [Towards Cost Sensitive Decision Making](https://mlsanity.com/paper/2410.03892/) (2024)
- [Attention when you need](https://mlsanity.com/paper/2501.07440/) (2025)
- [Robust Active Measuring under Model Uncertainty](https://mlsanity.com/paper/2312.11227/) (2023)
- [Online Planning in POMDPs with State-Requests](https://mlsanity.com/paper/2407.18812/) (2024)
- [MDPs with a State Sensing Cost](https://mlsanity.com/paper/2505.03280/) (2025)
- [Reinforcement Learning with Action-Triggered Observations](https://mlsanity.com/paper/2510.02149/) (2025)
- [Active Measuring in Reinforcement Learning With Delayed Negative Effects](https://mlsanity.com/paper/2510.14315/) (2025)
- [Optimizing Algorithms for Mobile Health Interventions with Active Querying Optimization](https://mlsanity.com/paper/2512.08950/) (2025)

## Abstract (arXiv)

We study Markov decision processes (MDPs), where agents have direct control over when and how they gather information, as formalized by action-contingent noiselessly observable MDPs (ACNO-MPDs). In these models, actions consist of two components: a control action that affects the environment, and a measurement action that affects what the agent can observe. To solve ACNO-MDPs, we introduce the act-then-measure (ATM) heuristic, which assumes that we can ignore future state uncertainty when choosing control actions. We show how following this heuristic may lead to shorter policy computation times and prove a bound on the performance loss incurred by the heuristic. To decide whether or not to take a measurement action, we introduce the concept of measuring value. We develop a reinforcement learning algorithm based on the ATM heuristic, using a Dyna-Q variant adapted for partially observable domains, and showcase its superior performance compared to prior methods on a number of partially-observable environments.