Model-based Bayesian Reinforcement Learning with Adaptive State Aggregation

نویسندگان

  • Cosmin Paduraru
  • Arthur Guez
  • Doina Precup
  • Joelle Pineau
چکیده

Model-based Bayesian reinforcement learning provides an elegant way of incorporating model uncertainty for trading off between exploration and exploitation. We propose an extension of modelbased Bayesian RL to continuous state spaces. The key feature of our approach is its search through the space of model structures, thus adapting not only the model parameters but also the structure itself to the problem at hand. We currently present algorithms and results for structures that are discretizations of the state space, but we hope to extend this to more powerful representations.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Model-based Bayesian Reinforcement Learning with Tree-based State Aggregation

Model-based Bayesian RL provides an elegant way of incorporating model uncertainty for trading off between exploration and exploitation. Yet, significant work remains to be done for extending model-based Bayesian RL to continuous state spaces; in this paper, we present one such extension. The key feature of our approach is its search through the space of model structures, thus adapting not only...

متن کامل

Adaptive Aggregation for Reinforcement Learning with Efficient Exploration: Deterministic Domains

We propose a model-based learning algorithm, the Adaptive Aggregation Algorithm (AAA), that aims to solve the online, continuous state space reinforcement learning problem in a deterministic domain. The proposed algorithm uses an adaptive state aggregation approach, going from coarse to fine grids over the state space, which enables to use finer resolution in the “important” areas of the state ...

متن کامل

Efficient Inverse Reinforcement Learning using Adaptive State-Graphs

Inverse Reinforcement Learning (IRL) provides a powerful mechanism for learning complex behaviors from demonstration by rationalizing such demonstrations. Unfortunately its applicability has been largely hindered by lack of powerful representations that can take advantage of various task affordances while still admitting scalability. Inspired by the success of sampling based approaches in class...

متن کامل

An Adaptive Learning Game for Autistic Children using Reinforcement Learning and Fuzzy Logic

This paper, presents an adapted serious game for rating social ability in children with autism spectrum disorder (ASD). The required measurements are obtained by challenges of the proposed serious game. The proposed serious game uses reinforcement learning concepts for being adaptive. It is based on fuzzy logic to evaluate the social ability level of the children with ASD. The game adapts itsel...

متن کامل

Reinforcement Learning with Soft

It is widely accepted that the use of more compact representations than lookup tables is crucial to scaling reinforcement learning (RL) algorithms to real-world problems. Unfortunately almost all of the theory of reinforcement learning assumes lookup table representations. In this paper we address the pressing issue of combining function approximation and RL, and present 1) a function approx-im...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2009