Skip to main content
Artificial Intelligence

Return to Question

added 6 characters in body; edited tags; edited title
Source Link
nbro
nbro
  • 41.4k
  • 12
  • 114
  • 205

Upper Is there an upper limit to the maximum cumulative reward in a deep reinforcement learning problem?

Is there an upper limit to the maximum cumulative reward in a deep reinforcement learning problem? 

For example, you want to train ana DQN agent in an environment, and you want to know what is the highest possible value you can get from the cumulative reward is, so you can compare this with your agents performance.

Upper limit to the maximum cumulative reward in a deep reinforcement learning problem

Is there an upper limit to the maximum cumulative reward in a deep reinforcement learning problem? For example you want to train an DQN agent in an environment and you want to know what is the highest possible value you can get from the cumulative reward, so you can compare this with your agents performance.

Is there an upper limit to the maximum cumulative reward in a deep reinforcement learning problem?

Is there an upper limit to the maximum cumulative reward in a deep reinforcement learning problem? 

For example, you want to train a DQN agent in an environment, and you want to know what the highest possible value you can get from the cumulative reward is, so you can compare this with your agents performance.

Became Hot Network Question
Source Link
user38696
user38696

Upper limit to the maximum cumulative reward in a deep reinforcement learning problem

Is there an upper limit to the maximum cumulative reward in a deep reinforcement learning problem? For example you want to train an DQN agent in an environment and you want to know what is the highest possible value you can get from the cumulative reward, so you can compare this with your agents performance.