Skip to content

Using the "Advantage Actor Critic(A2C)" Reinforcement Learning method, the 'Agent' is trained to play Atari's Breakout.

Notifications You must be signed in to change notification settings

AnuraagRath/A.I-learns-to-play-Atari-Breakout-ReinforcementLearning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 

Repository files navigation

A.I learns to play Atari's Breakout (Reinforcement Learning)-

Using the "Advantage Actor Critic(A2C)" Reinforcement Learning method, the A.I is trained to play Atari's Breakout.

The Game:

The game used for this Model is Atari's Breakout

breakoutGame

The game was used by downloading ROM files.

AtariMania 'ROMS'

importingbreakoutGame

The Algorithm:

The A2C algortihm has been implemented for the Agent to play the game

refer the paper:

Asynchronous Methods for Deep Reinforcement Learning

The Python Libraries used:

StableBaselines-3

OpenAI-Gym

Models:

  • Mark I (100k TimeSteps):

The first Model is a Preliminary Model which has been trained with 100k TimeSteps.

100k

Highest Score:

100KScore

  • Mark II (2M TimeSteps):

The Second model is an improved model that has been trained for 2 Million TimeSteps. The Performance was significantly better

2M

Highest Score:

2MScore

Tensorboard:

These show as to how the Model kept getting better and better, where the Agent was able to score higher.

2MScore

2MScore

2MScore

Better Performance:

The Agent was able to score way better with the 2M TimeSteps trained Model while Testing.

2MScore

2MScore

2MScore

If the Model were to be trained for longer TimeSteps, it would perform more effectively.

Have Fun

Yours Truely,

Anuraag Rath :P

About

Using the "Advantage Actor Critic(A2C)" Reinforcement Learning method, the 'Agent' is trained to play Atari's Breakout.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published