On the Reduction of Variance and Overestimation of Deep Q-Learning

10/14/2019
by   Mohammed Sabry, et al.
0

The breakthrough of deep Q-Learning on different types of environments revolutionized the algorithmic design of Reinforcement Learning to introduce more stable and robust algorithms, to that end many extensions to deep Q-Learning algorithm have been proposed to reduce the variance of the target values and the overestimation phenomena. In this paper, we examine new methodology to solve these issues, we propose using Dropout techniques on deep Q-Learning algorithm as a way to reduce variance and overestimation. We further present experiments on some of the benchmark environments that demonstrate significant improvement of the stability of the performance and a reduction in variance and overestimation.

READ FULL TEXT
research
11/07/2016

Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning

Instability and variability of Deep Reinforcement Learning (DRL) algorit...
research
05/20/2019

Stochastic Variance Reduction for Deep Q-learning

Recent advances in deep reinforcement learning have achieved human-level...
research
04/24/2020

Evolution of Q Values for Deep Q Learning in Stable Baselines

We investigate the evolution of the Q values for the implementation of D...
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...
research
03/02/2022

Improving the Diversity of Bootstrapped DQN via Noisy Priors

Q-learning is one of the most well-known Reinforcement Learning algorith...
research
11/23/2021

Variance Reduction in Deep Learning: More Momentum is All You Need

Variance reduction (VR) techniques have contributed significantly to acc...
research
12/01/2020

Obtain Employee Turnover Rate and Optimal Reduction Strategy Based On Neural Network and Reinforcement Learning

Nowadays, human resource is an important part of various resources of en...

Please sign up or login with your details

Forgot password? Click here to reset