3 votes
Accepted

How does the RL agent understand motion if it gets only one image as input?

In the article Playing Atari with Deep Reinforcement Learning, Mnih et al, 2013, which was a major outbreak in Deep Reinforcement learning (especially in Deep Q learning), they don't feed only the ...
16Aghnar's user avatar
  • 601
3 votes
Accepted

Was DeepMind's DQN learning simultaneously all the Atari games?

Switching required a re-learn. Also, note that: We use the same network architecture, learning algorithm and hyperparameters settings across all seven games, showing that our approach is robust ...
Franck Dernoncourt's user avatar
2 votes
Accepted

Why should the agent bounce the ball back and forth on the same side of the screen in Atari Breakout?

There might be some cases, say, once the agent clearing a brick obtaining a positive reward and then forever bouncing the ball on the same side of the screen would have a higher cumulative reward than ...
cinch's user avatar
  • 2,307
2 votes
Accepted

How can I use a ResNet as a function approximator for pixel based reinforcement learning?

Residual Network are usually deeper and hence take more time to train. EfficientNet are trying to tackle this. However, the latest advice show that the architecture tend to play a crucial role in the ...
Quentin Delfosse's user avatar
2 votes

Was DeepMind's DQN learning simultaneously all the Atari games?

Switching requires relearning, the network did not have a single set of weights that allowed it to play all games well. This is due to the catastrophic forgetting problem. However, recent work has ...
Nix's user avatar
  • 21
1 vote

IQN bellman target: using Z vs using Q

Replacement you suggest is replacement of random variable by its expectation in forward part of TD. It would make IQN into modification of C51 with randomly sampled function approximator instead of ...
mirror2image's user avatar
1 vote

DQN stuck at suboptimal policy in Atari Pong task

Incase you still haven't been able to resolve the problem, here's a link to the answer to my own question, which has the step-wise changes I made to achieve a +18 average score saturation using just a ...
hridayns's user avatar
  • 233

Only top scored, non community-wiki answers of a minimum length are eligible