Skip to content

thegreatshasha/atari_ai

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

40 Commits

games

games

 
 

ALGORITHM.md

ALGORITHM.md

 
 

README.md

README.md

 
 

deepmind.pdf

deepmind.pdf

 
 

helpers.py

helpers.py

 
 

helpers.pyc

helpers.pyc

 
 

install_ubuntu.sh

install_ubuntu.sh

 
 

ring_buffer.py

ring_buffer.py

 
 

select_with_probability.py

select_with_probability.py

 
 

task_queue.py

task_queue.py

 
 

test_bak.py

test_bak.py

 
 

test_simple.py

test_simple.py

 
 

tests.py

tests.py

 
 

transition_table.py

transition_table.py

 
 

visualize.py

visualize.py

 
 

Repository files navigation

Atari player ai Agent3

Based on the deepmind paper on deep Q reinforcement learning. Learns an optimum action policy from pixel level data.

Python interface instructions

Python interface instructions are available here https://github.com/bbitmaster/ale_python_interface/wiki/Code-Tutorial

The game

We tested the agent on a really simple game, dodge the brick. The aim of the game is for the green brick to dodge the onslaught of the falling red bricks The score policy is +1/-30 to weed out the random agents. +1 points for surviving in each frame and -30 for colliding with the red brick and dying.

Screenshots

A simple agent which does nothing but just sits around

Agent0

This agent just sits around doing nothing. It doesn't take any action, left or right. Looks like someone needs a little motivation in life.

Random agent

Agent1

An agent which oscillates a lot, staying at the same place rougly. It also runs into the red brick a lot and isn't really being affected by the red brick's presence.

25% accuracy

Agent2

An agent which tries to move away from the red brick and find a safe spot. It gets a score of 2529/10000 = 25% accuracy. The agent still oscillates a lot but lesser than first case. It does run into the red brick occasionally though.

86% accuracy

Agent3

An agent which has learnt to dodge the red brick effectively. It get a score of 8698/10000 = 86% accuracy. The agent has learnt that oscillating to and fro heavily is not a really helpful policy and hence is a lot calmer.

It also never runs into the red brick anymore, dodging it like a master samurai.

Running on the rest of atari games

Coming soon

About

No description, website, or topics provided.

Resources

Readme
Activity

Stars

1 star

Watchers

1 watching

Forks

0 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages