Stack Overflow
Stack Overflow

Questions tagged [atari-2600]

13 questions
3
votes
1 answer

I want my player to move while the button is pressed

So when i do movement only at one side, it works but once i finish them all, it doesn't work. I tried to switch the numbers, commands, but it was useless. I'm a begginer and my skills are not too good for this because I was using tutorials before. i…
voltifer
  • 18
  • 10
2
votes
0 answers

Done status based on action in OpenAI Atari

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…
niallmandal
  • 119
  • 10
1
vote
1 answer

Does it matter how you fill the end of ROM in Atari 2600 code?

Excuse my probably mistake-full question. Im learning to make games for Atari 2600 for fun. So this is my code: ; Welcome processor 6502 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;; ; include your macros…
Alireza Amani
  • 57
  • 2
  • 7
1
vote
2 answers

How to check out actions available in OpenAI gym environment?

It seems like the list of actions for Open AI Gym environments are not available to check out even in the documentation. For example, let's say you want to play Atari Breakout. The available actions will be right, left, up, and…
Ji Hwan Park
  • 11
  • 2
1
vote
0 answers

Q values overshoot in Double Deep Q Learning

I am trying to teach the agent to play ATARI Space Invaders video game, but my Q values overshoot. I have clipped positive rewards to 1 (agent also receives -1 for losing a life), so the maximum expected return should be around 36 (maybe I am wrong…
Heisenberg666
  • 42
  • 5
1
vote
1 answer

How to run and render gym Atari environments in real time, instead of sped up?

Currently when I render any Atari environments they are always sped up, and I want to look at them in normal speed. I am using Gym Atari with Tensorflow, and Keras-rl on Windows. The language is python.
PancakeFactory
  • 19
  • 4
0
votes
1 answer

Resize a state of a gym environment composed by 4 frames (atari environment)

I'm developing an Autonomous Agent based on DQN. I am using the gym library to make the environments that I want to test, but I'm stuck in processing the frames of the state. The state that the gym environment returns, using the FrameStack wrapper,…
Luca Varini
  • 1
  • 1
0
votes
0 answers

Using gym atari (version 0.9.5) in python on windows

Im trying to install the gym atari package on version 0.9.5 (I specifically need this version), but when I run the code (which is supposed to be running smoothly if gym is properly downloaded), I get the following error: AttributeError: 'AtariEnv'…
nir shahar
  • 194
  • 1
  • 8
0
votes
0 answers

DDQN not training on breakout

I'm trying to get Breakout going based on a implemented version of Double Deep Q Network. My problem is that I don't see any improvement even after 6000 episodes. At first sight I also don't see any problems with the hyperparameter set up: gamma =…
Sunshine
  • 75
  • 7
0
votes
0 answers

How to fix neural network for deep q learning?

I have recently attempted to create deep q learning with keras in google colab. The two problems are that The error "Failed to convert a NumPy array to a Tensor (Unsupported object type generator)." is shown in the line: "next_q_value =…
user12852585
  • 59
  • 2
0
votes
0 answers

Can this solution for the Entombed maze lookup table be further simplified?

After channelling my lockdown spirit, I figured I'd wave my axe at the infamous puzzle of finding an algorithmic solution for the lookup table used for maze generation in the game Entombed (Atari 2600). I came up with this pseudocode: function…
user2464424
  • 1,456
  • 1
  • 12
  • 25
0
votes
0 answers

DQN not able to learn Atari game

Hello I'm trying to implement DQN Agent to play Atari-Pong game. But still after 500.000 parameter updates, the model still scores -21. This is my code, do you have any idea what could be wrong? Replaybuffer import random as r from collections…
mAI
  • 59
  • 1
  • 3
0
votes
0 answers

Four-way Gravitational Engine Issues (Atari 2600)

In the last couple months I've been working on a project using "Fake Gravity Platformer Test with Shooting" (from here: http://atariage.com/forums/topic/179473-fake-gravity-platformer-test/) as a template. The goal of my project is to create a…
Angel Sachse
  • 19
  • 2