2

I am attempting to create a neural network to play the emulated atari game "BreakoutDeterministic". The action space for the game is [0,1,2,3].

When inputting

frame, reward, is_done, _ = env.step(env.action_space.sample())

The game will play out and and the "is_done" variable will eventually be set to True (when the game ends)

When inputting

frame, reward, is_done, _ = env.step(3)

The game will end but done will not be set to True. Instead I have to manually end the process.

Any explanation to why this happens and how I can fix it?

Full code:

import gym

env = gym.make('BreakoutDeterministic-v4')
frame = env.reset()
env.render()

is_done = False
while not is_done:
  frame, reward, is_done, _ = env.step(env.action_space.sample())
  #frame, reward, is_done, _ = env.step(3)
  env.render()
niallmandal
  • 119
  • 10
  • Thought it's something to do with the recently updated version. No luck after rolling back though. It starts fine, but then after a few training iterations done is never true. Every session is forcefully interrupted. – Eugene Kostrikov Feb 22 '19 at 22:38

0 Answers0