DeepAI

Chrome Dino Run using Reinforcement Learning

08/15/2020

∙

by Divyanshu Marwah, et al.

∙

∙

Reinforcement Learning is one of the most advanced set of algorithms known to mankind which can compete in games and perform at par or even better than humans. In this paper we study most popular model free reinforcement learning algorithms along with convolutional neural network to train the agent for playing the game of Chrome Dino Run. We have used two of the popular temporal difference approaches namely Deep Q-Learning, and Expected SARSA and also implemented Double DQN model to train the agent and finally compare the scores with respect to the episodes and convergence of algorithms with respect to timesteps.

READ FULL TEXT

Divyanshu Marwah
1 publication
Sneha Srivastava
1 publication
Anusha Gupta
1 publication
Shruti Verma
1 publication

∙ 03/21/2020

FlapAI Bird: Training an Agent to Play Flappy Bird Using Reinforcement Learning Techniques

Reinforcement learning is one of the most popular approach for automated...

Tai Vu, et al. ∙

∙ 09/10/2019

Reinforcement Learning and Video Games

Reinforcement learning has exceeded human-level performance in game play...

Yue Zheng, et al. ∙

∙ 09/03/2022

Model-Free Deep Reinforcement Learning in Software-Defined Networks

This paper compares two deep reinforcement learning approaches for cyber...

Luke Borchjes, et al. ∙

∙ 11/05/2017

Double Q(σ) and Q(σ, λ): Unifying Reinforcement Learning Control Algorithms

Temporal-difference (TD) learning is an important field in reinforcement...

Markus Dumke, et al. ∙

∙ 02/07/2021

Sparsely ensembled convolutional neural network classifiers via reinforcement learning

We consider convolutional neural network (CNN) ensemble learning with th...

Roman Malashin, et al. ∙

∙ 02/27/2021

Multi-agent Reinforcement Learning in OpenSpiel: A Reproduction Report

In this report, we present results reproductions for several core algori...

Michael Walton, et al. ∙

∙ 11/04/2021

Model-Free Risk-Sensitive Reinforcement Learning

We extend temporal-difference (TD) learning in order to obtain risk-sens...

Grégoire Delétang, et al. ∙