Learning Principle of Least Action with Reinforcement Learning

11/24/2020
by   Zehao Jin, et al.
0

Nature provides a way to understand physics with reinforcement learning since nature favors the economical way for an object to propagate. In the case of classical mechanics, nature favors the object to move along the path according to the integral of the Lagrangian, called the action 𝒮. We consider setting the reward/penalty as a function of 𝒮, so the agent could learn the physical trajectory of particles in various kinds of environments with reinforcement learning. In this work, we verified the idea by using a Q-Learning based algorithm on learning how light propagates in materials with different refraction indices, and show that the agent could recover the minimal-time path equivalent to the solution obtained by Snell's law or Fermat's Principle. We also discuss the similarity of our reinforcement learning approach to the path integral formalism.

READ FULL TEXT

Authors

page 1

page 2

page 3

page 4

04/26/2016

Tournament selection in zeroth-level classifier systems based on average reward reinforcement learning

As a genetics-based machine learning technique, zeroth-level classifier ...
08/13/2020

Reinforcement Learning with Trajectory Feedback

The computational model of reinforcement learning is based upon the abil...
02/01/2022

Reinforcement learning of optimal active particle navigation

The development of self-propelled particles at the micro- and the nanosc...
10/12/2017

Is Epicurus the father of Reinforcement Learning?

The Epicurean Philosophy is commonly thought as simplistic and hedonisti...
02/07/2021

Sparsely ensembled convolutional neural network classifiers via reinforcement learning

We consider convolutional neural network (CNN) ensemble learning with th...
09/02/2019

Evolutionary reinforcement learning of dynamical large deviations

We show how to calculate dynamical large deviations using evolutionary r...
06/30/2019

Reinforcement Learning for Robotic Time-optimal Path Tracking Using Prior Knowledge

Time-optimal path tracking, as a significant tool for industrial robots,...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.