Emergence of Structured Behaviors from Curiosity-Based Intrinsic Motivation

02/21/2018
by   Nick Haber, et al.
0

Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to replicate some of these abilities with a neural network that implements curiosity-driven intrinsic motivation. Using a simple but ecologically naturalistic simulated environment in which the agent can move and interact with objects it sees, the agent learns a world model predicting the dynamic consequences of its actions. Simultaneously, the agent learns to take actions that adversarially challenge the developing world model, pushing the agent to explore novel and informative interactions with its environment. We demonstrate that this policy leads to the self-supervised emergence of a spectrum of complex behaviors, including ego motion prediction, object attention, and object gathering. Moreover, the world model that the agent learns supports improved performance on object dynamics prediction and localization tasks. Our results are a proof-of-principle that computational models of intrinsic motivation might account for key features of developmental visuomotor learning in infants.

READ FULL TEXT

page 1

page 5

research
02/21/2018

Learning to Play with Intrinsically-Motivated Self-Aware Agents

Infants are experts at playing, with an amazing ability to generate nove...
research
07/27/2020

Noisy Agents: Self-supervised Exploration by Predicting Auditory Events

Humans integrate multiple sensory modalities (e.g. visual and audio) to ...
research
06/19/2019

Control What You Can: Intrinsically Motivated Task-Planning Agent

We present a novel intrinsically motivated agent that learns how to cont...
research
06/03/2014

Changing the Environment Based on Empowerment as Intrinsic Motivation

One aspect of intelligence is the ability to restructure your own enviro...
research
05/22/2023

Measuring and Modeling Physical Intrinsic Motivation

Humans are interactive agents driven to seek out situations with interes...
research
12/29/2022

Intrinsic Motivation in Dynamical Control Systems

Biological systems often choose actions without an explicit reward signa...
research
07/06/2019

Intrinsic Motivation Driven Intuitive Physics Learning using Deep Reinforcement Learning with Intrinsic Reward Normalization

At an early age, human infants are able to learn and build a model of th...

Please sign up or login with your details

Forgot password? Click here to reset