# OpenAI-Gym excess of actions

I'm trying to replicate the DeepMind DQN paper, and actually I'm using the OpenAI-Gym enviroment. I'm trying to get a decent score with Space Invaders (using SpaceInvaders-v4 enviroment). I checked the number of actions available with env.unwrapped.get_action_meanings() and I get this:

['NOOP', 'FIRE', 'RIGHT', 'LEFT', 'RIGHTFIRE', 'LEFTFIRE']


Checking the number of actions with env.action_space.n gives me a number of 6 actions. The 'RIGHTFIRE' and 'LEFTFIRE' actions I suppose isn't used, am I right? If so, restricting the action size to the 4 first actions would improve my learning?

• It would learn faster since there are less actions to explore, but how did you conclude that RIGHTFIRE and LEFTFIRE actions aren't used ? – Brale Mar 13 '19 at 22:06
• @Brale_ I tried and they do the same as LEFT and RIGHT. If I'm wrong please someone tell me. – JCP Mar 13 '19 at 22:52
• Did you mean SpaceInvaders-v0? – Philip Raeisghasem Mar 14 '19 at 2:32
• @PhilipRaeisghasem No, SpaceInvaders-v4. It's basically the same as v0 but improved. – JCP Mar 14 '19 at 2:49
• Could you provide a link? I can't seem to find it – Philip Raeisghasem Mar 14 '19 at 2:50