# Experimental results : Reinforcement Learning of POMDPs using Spectral Methods

arXiv: https://arxiv.org/abs/1705.02553 · HTML: https://mlsanity.com/paper/1705.02553/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2017.

## Built on by (most cited first, 1 of 1)

- [Online Learning for Unknown Partially Observable MDPs](https://mlsanity.com/paper/2102.12661/) (2021)

## Abstract (arXiv)

We propose a new reinforcement learning algorithm for partially observable Markov decision processes (POMDP) based on spectral decomposition methods. While spectral methods have been previously employed for consistent learning of (passive) latent variable models such as hidden Markov models, POMDPs are more challenging since the learner interacts with the environment and possibly changes the future observations in the process. We devise a learning algorithm running through epochs, in each epoch we employ spectral techniques to learn the POMDP parameters from a trajectory generated by a fixed policy. At the end of the epoch, an optimization oracle returns the optimal memoryless planning policy which maximizes the expected reward based on the estimated POMDP model. We prove an order-optimal regret bound with respect to the optimal memoryless policy and efficient scaling with respect to the dimensionality of observation and action spaces.