For questions related to the Atari games, which are often used in reinforcement learning (RL) as standard problems to test new RL algorithms or methods.
Questions tagged [atari-games]
15 questions
10
votes
2 answers
Was DeepMind's DQN learning simultaneously all the Atari games?
DeepMind states that its deep Q-network (DQN) was able to continually adapt its behavior while learning to play 49 Atari games.
After learning all games with the same neural net, was the agent able to play them all at 'superhuman' levels…
Dion
- 203
- 2
- 6
4
votes
1 answer
DQN stuck at suboptimal policy in Atari Pong task
I am in the process of implementing the DQN model from scratch in PyTorch with the target environment of Atari Pong. After a while of tweaking hyper-parameters, I cannot seem to get the model to achieve the performance that is reported in most…
Mink
- 191
- 5
2
votes
0 answers
When can we say an RL algorithm learns an Atari game?
If an Atari game's rewards can be between $-100$ and $100$, when can we say an agent learned to play this game? Should it get the reward very close to $100$ for each instance of the game? Or it is fine if it gets a low score (say $-100$) at some…
user491626
- 241
- 1
- 4
2
votes
0 answers
Minimax evaluation function for games with score instead of loss/draw/win result
I am trying to create minimax evaluation function for the Ms Pacman game. The goal of the player is to maximize score.
I have some idea about the features that I would like to use in my evaluation function (which is weighted sum of all…
Druudik
- 159
- 7
2
votes
0 answers
Demonstration of AI-powered Mario collecting lots of coins?
As part of a talk I'm giving, I'd like to show one of the many videos on YouTube where an AI is playing Mario, such as this one. What bothers me though is that the AI is trying to complete the level as quickly as possible, without trying to collect…
Ram Rachum
- 261
- 1
- 9
2
votes
0 answers
How was the DQN trained to play many games?
Some people claim that DQN was used to play many Atari games. But what actually happened? Was DQN trained only once (with some data from all games) or was it trained separately for each game? What was common to all those games? Only the architecture…
mason7663
- 603
- 3
- 10
1
vote
1 answer
How can I use a ResNet as a function approximator for pixel based reinforcement learning?
I'd like to use a residual network to improve learning in image-based reinforcement learning, specifically on Atari Games.
My main question is divided into 3 parts.
Would it be wise to integrate a generic ResNet with a DQN variant?
I believe…
desert_ranger
- 586
- 3
- 19
1
vote
0 answers
Too slow search using MCTS in OpenAI Atari games
I'm recently using Monte Carlo Tree Search in OpenAi Gym Atari, but the result isn't satisfying.
Without render, the game lasts about 180 steps ( env.step() was called this much time ) with random agent. However, my MCTS agent only made the game…
Dibbla
- 11
- 2
1
vote
1 answer
Why does the Atari Gym Amidar environment only move after a certain number of episodes?
When I try to run Amidar even without RL code, I cannot get the environment to move immediately. It takes about 100 steps before the game actually starts moving. I use the following simple code to display some images and print some actions (I always…
Lennart
- 113
- 2
1
vote
1 answer
How does the RL agent understand motion if it gets only one image as input?
Basic deep reinforcement learning methods use as input an image for the current state, do some convolutions on that image, apply some reinforcement learning algorithm, and it is solved.
Let us take the game Breakout or Pong as an example. What I do…
devidduma
- 532
- 3
- 10
1
vote
0 answers
Why isn't my DQN agent improving when trained on Atari Breakout?
Lately, I have implemented DQN for Atari Breakout. Here is the code:
https://github.com/JeremieGauthier/AI_Exercices/blob/master/Atari_Breakout/DQN_Breakout.py
I have trained the agent for over 1500 episodes, but the training leveled off at around…
jgauth
- 161
- 10
1
vote
1 answer
IQN bellman target: using Z vs using Q
IQN paper (https://arxiv.org/abs/1806.06923) uses distributional bellman target:
$$ \delta^{\tau,\tau'}_t = r_t + \gamma Z_{\tau'}(x_{t+1}, \pi_{\beta}(x_{t+1})) - Z_{\tau}(x_t, a_t) $$
And optimizes:
$$ L = \frac{1}{N'} \sum^{N}_i \sum^{N'}_j…
Domas A
- 58
- 5
0
votes
0 answers
When should grayscale processing be applied to image inputs in visual reinforcement learning environments?
I am currently working with visual environments in Reinforcement Learning (RL) and have noticed differing practices regarding preprocessing of image inputs. Specifically, in the Atari environment, a common approach is to first convert RGB images to…
XiaoBanni
- 41
- 4
0
votes
0 answers
how to handle different objectives in Atari games in reinforcement learning
My impression on DeepMind's Deep-Q RL for learning Atari games paper is that it uses the same model to learn to play multiple different games at the same time. I wonder how did the RL agent learn in such a setting. In particular, when the game…
Sam
- 175
- 5
0
votes
0 answers
How to train a hierarchical DQN to play the Montezuma's Revenge game?
Would anybody share the experience on how to train a hierarchical DQN to play the Montezuma's Revenge game? How should I design the reward function? How should I balance the anneal rate of the two-level?
I've been trying to train an agent to solve…
zhma
- 1
- 1