For questions related to the concept of return in reinforcement learning, which is defined as the future cumulative (discounted) reward or, in simple words, the reward in the long run.
About
Stats
|
created |
4 years, 1 month ago |
|
viewed |
4 times |
|
active |
2 years, 4 months ago |
|
editors |
1 |
Top Answerers
more »
Recent Hot Answers
Why are lambda returns so rarely used in policy gradients?Why are lambda returns so rarely used in policy gradients?
What is the difference between expected return and value function?
Is there any difference between reward and return in reinforcement learning?
How can the $\lambda$-return be defined recursively?
more »