AI Chat AI Image Generator AI Video Text to Speech

Noise, overestimation and exploration in Deep Reinforcement Learning

06/25/2020

∙

by Rafael Stekolshchik, et al.

∙

∙

We will discuss some statistical noise related phenomena, that were investigated by different authors in the framework of Deep Reinforcement Learning algorithms. The following algorithms are touched: DQN, Double DQN, DDPG, TD3, Hill-Climbing. Firstly, we consider overestimation, that is the harmful property resulting from noise. Then we deal with noise used for exploration, this is the useful noise. We discuss setting the noise parameter in TD3 for typical PyBullet environments associated with articulate bodies such as HopperBulletEnv and Walker2DBulletEnv. In the appendix, in relation with the Hill-Climbing algorithm, we will look at one more example of noise: adaptive noise.

research

∙ 03/23/2022

An Optical Controlling Environment and Reinforcement Learning Benchmarks

Deep reinforcement learning has the potential to address various scienti...

0 Abulikemu Abuduweili, et al. ∙

research

∙ 06/19/2020

NROWAN-DQN: A Stable Noisy Network with Noise Reduction and Online Weight Adjustment for Exploration

Deep reinforcement learning has been applied more and more widely nowada...

0 Shuai Han, et al. ∙

research

∙ 02/13/2023

Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning

Tomorrow's robots will need to distinguish useful information from noise...

6 Bram Grooten, et al. ∙

research

∙ 06/08/2022

Action Noise in Off-Policy Deep Reinforcement Learning: Impact on Exploration and Performance

Many deep reinforcement learning algorithms rely on simple forms of expl...

0 Jakob Hollenstein, et al. ∙

research

∙ 06/21/2018

How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments

Consistently checking the statistical significance of experimental resul...

4 Cédric Colas, et al. ∙

research

∙ 09/18/2018

Switching Isotropic and Directional Exploration with Parameter Space Noise in Deep Reinforcement Learning

This paper proposes an exploration method for deep reinforcement learnin...

0 Izumi Karino, et al. ∙

research

∙ 07/01/2019

Designing Deep Reinforcement Learning for Human Parameter Exploration

Software tools for generating digital sound often present users with hig...

0 Hugo Scurto, et al. ∙