DeepAI AI Chat
Log In Sign Up

Learning Efficient Representation for Intrinsic Motivation

by   Ruihan Zhao, et al.
berkeley college

Mutual Information between agent Actions and environment States (MIAS) quantifies the influence of agent on its environment. Recently, it was found that the maximization of MIAS can be used as an intrinsic motivation for artificial agents. In literature, the term empowerment is used to represent the maximum of MIAS at a certain state. While empowerment has been shown to solve a broad range of reinforcement learning problems, its calculation in arbitrary dynamics is a challenging problem because it relies on the estimation of mutual information. Existing approaches, which rely on sampling, are limited to low dimensional spaces, because high-confidence distribution-free lower bounds for mutual information require exponential number of samples. In this work, we develop a novel approach for the estimation of empowerment in unknown dynamics from visual observation only, without the need to sample for MIAS. The core idea is to represent the relation between action sequences and future states using a stochastic dynamic model in latent space with a specific form. This allows us to efficiently compute empowerment with the "Water-Filling" algorithm from information theory. We construct this embedding with deep neural networks trained on a sophisticated objective function. Our experimental results show that the designed embedding preserves information-theoretic properties of the original dynamics.


page 7

page 8


Empowerment-driven Exploration using Mutual Information Estimation

Exploration is a difficult challenge in reinforcement learning and is of...

Intrinsic Motivation in Dynamical Control Systems

Biological systems often choose actions without an explicit reward signa...

Mutual Information-based State-Control for Intrinsically Motivated Reinforcement Learning

In reinforcement learning, an agent learns to reach a set of goals by me...

Information is Power: Intrinsic Control via Information Capture

Humans and animals explore their environment and acquire useful skills e...

Empowerment for Continuous Agent-Environment Systems

This paper develops generalizations of empowerment to continuous states....

Changing the Environment Based on Empowerment as Intrinsic Motivation

One aspect of intelligence is the ability to restructure your own enviro...

Efficient Empowerment

Empowerment quantifies the influence an agent has on its environment. Th...