Visceral Machines: Reinforcement Learning with Intrinsic Rewards that Mimic the Human Nervous System

05/25/2018
by   Daniel McDuff, et al.
2

The human autonomic nervous system has evolved over millions of years and is essential for survival and responding to threats. As people learn to navigate the world, "fight or flight" responses provide intrinsic feedback about the potential consequence of action choices (e.g., becoming nervous when close to a cliff edge or driving fast around a bend.) We present a novel approach to reinforcement learning that leverages a task-independent intrinsic reward function that mimics human autonomic nervous system responses based on peripheral pulse measurements. Our hypothesis is that such reward functions can circumvent the challenges associated with sparse and skewed rewards in reinforcement learning settings and can help improve sample efficiency. We test this in a simulated driving environment and show that it can increase the speed of learning and reduce the number of collisions during the learning stage.

READ FULL TEXT

page 4

page 6

research
02/21/2023

Curiosity-driven Exploration in Sparse-reward Multi-agent Reinforcement Learning

Sparsity of rewards while applying a deep reinforcement learning method ...
research
12/01/2019

Affect-based Intrinsic Rewards for Learning General Representations

Positive affect has been linked to increased interest, curiosity and sat...
research
02/25/2020

Human Apprenticeship Learning via Kernel-based Inverse Reinforcement Learning

This paper considers if a reward function learned via inverse reinforcem...
research
10/07/2022

Generative Augmented Flow Networks

The Generative Flow Network is a probabilistic framework where an agent ...
research
05/18/2017

Feature Control as Intrinsic Motivation for Hierarchical Reinforcement Learning

The problem of sparse rewards is one of the hardest challenges in contem...
research
06/19/2019

Adapting Behaviour via Intrinsic Reward: A Survey and Empirical Study

Learning about many things can provide numerous benefits to a reinforcem...
research
08/01/2019

Curiosity-driven Reinforcement Learning for Diverse Visual Paragraph Generation

Visual paragraph generation aims to automatically describe a given image...

Please sign up or login with your details

Forgot password? Click here to reset