# Data-Efficient Reinforcement Learning in Continuous-State POMDPs

arXiv: https://arxiv.org/abs/1602.02523 · HTML: https://mlsanity.com/paper/1602.02523/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Feb 2016.

## Built on by (most cited first, 2 of 2)

- [Certification of Iterative Predictions in Bayesian Neural Networks](https://mlsanity.com/paper/2105.10134/) (2021)
- [FACTS: A Factored State-Space Framework For World Modelling](https://mlsanity.com/paper/2410.20922/) (2024)

## Abstract (arXiv)

We present a data-efficient reinforcement learning algorithm resistant to observation noise. Our method extends the highly data-efficient PILCO algorithm (Deisenroth & Rasmussen, 2011) into partially observed Markov decision processes (POMDPs) by considering the filtering process during policy evaluation. PILCO conducts policy search, evaluating each policy by first predicting an analytic distribution of possible system trajectories. We additionally predict trajectories w.r.t. a filtering process, achieving significantly higher performance than combining a filter with a policy optimised by the original (unfiltered) framework. Our test setup is the cartpole swing-up task with sensor noise, which involves nonlinear dynamics and requires nonlinear control.