ABC Reinforcement Learning

03/27/2013
by   Christos Dimitrakakis, et al.
0

This paper introduces a simple, general framework for likelihood-free Bayesian reinforcement learning, through Approximate Bayesian Computation (ABC). The main advantage is that we only require a prior distribution on a class of simulators (generative models). This is useful in domains where an analytical probabilistic model of the underlying process is too complex to formulate, but where detailed simulation models are available. ABC-RL allows the use of any Bayesian reinforcement learning technique, even in this case. In addition, it can be seen as an extension of rollout algorithms to the case where we do not know what the correct model to draw rollouts from is. We experimentally demonstrate the potential of this approach in a comparison with LSPI. Finally, we introduce a theorem showing that ABC is a sound methodology in principle, even when non-sufficient statistics are used.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/11/2013

Monte-Carlo utility estimates for Bayesian reinforcement learning

This paper introduces a set of algorithms for Monte-Carlo Bayesian reinf...
research
11/03/2022

Reinforcement Learning in Non-Markovian Environments

Following the novel paradigm developed by Van Roy and coauthors for rein...
research
09/14/2016

Bayesian Reinforcement Learning: A Survey

Bayesian methods for machine learning have been widely investigated, yie...
research
05/02/2018

Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review

The framework of reinforcement learning or optimal control provides a ma...
research
09/14/2015

Benchmarking for Bayesian Reinforcement Learning

In the Bayesian Reinforcement Learning (BRL) setting, agents try to maxi...
research
05/08/2013

Cover Tree Bayesian Reinforcement Learning

This paper proposes an online tree-based Bayesian approach for reinforce...
research
05/22/2022

A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learning

While reinforcement learning (RL) algorithms are achieving state-of-the-...

Please sign up or login with your details

Forgot password? Click here to reset