Chrome Dino Run using Reinforcement Learning

TL;DR

This paper applies advanced reinforcement learning algorithms, including Deep Q-Learning, Expected SARSA, and Double DQN, combined with CNNs, to train an agent to play Chrome Dino Run, analyzing their performance and convergence.

Contribution

It introduces the application of multiple RL algorithms with CNNs to Chrome Dino Run and compares their effectiveness and convergence behavior.

Findings

Double DQN outperforms other algorithms in score stability.

All algorithms successfully learned to play the game.

Convergence times vary among the tested RL methods.

Abstract

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.