Reinforcement Learning of POMDPs using Spectral Methods - Archive ouverte HAL Access content directly
Conference Papers Year : 2016

Reinforcement Learning of POMDPs using Spectral Methods

(1) , (2, 3) , (1)
1
2
3

Abstract

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 episodes, in each episode we employ spectral techniques to learn the POMDP parameters from a trajectory generated by a fixed policy. At the end of the episode, 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 w.r.t. the optimal memoryless policy and efficient scaling with respect to the dimensionality of observation and action spaces.
Fichier principal
Vignette du fichier
master.pdf (1001.49 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01322207 , version 1 (26-05-2016)

Identifiers

  • HAL Id : hal-01322207 , version 1

Cite

Kamyar Azizzadenesheli, Alessandro Lazaric, Animashree Anandkumar. Reinforcement Learning of POMDPs using Spectral Methods. Proceedings of the 29th Annual Conference on Learning Theory (COLT2016), Jun 2016, New York City, United States. ⟨hal-01322207⟩
185 View
114 Download

Share

Gmail Facebook Twitter LinkedIn More