Skip to main content
edited title
Link
nbro
  • 41.4k
  • 12
  • 114
  • 205

Discrete Action Space Why does each component of the tuple that represents an action have a categorical distribution in the TRPO paper J Schulman 2015?

added 2 characters in body
Source Link
nbro
  • 41.4k
  • 12
  • 114
  • 205

I was going through the TRPO paper, and there was a line under Appendix D "Approximating Factored Policies with Neural Networks" in the last paragraph which I am unable to understand

The action consists of a tuple $(a_1, a_2..... , a_K)$ of integers $a_k\in\{1, 2,......,N_k\} $ and each of these components is assumed to have a categorical distribution.

I can't seem to get how each component has a categorical distribution. I think it should be the tuple that has a categorical distribution. I think I am getting something wrong.

I was going through the TRPO paper, and there was a line under Appendix D "Approximating Factored Policies with Neural Networks" in the last paragraph which I am unable to understand

The action consists of a tuple $(a_1, a_2..... , a_K)$ of integers $a_k\in\{1, 2,......,N_k\} $ and each of these components is assumed to have a categorical distribution.

I can't seem to get how each component has categorical distribution. I think it should be the tuple that has a categorical distribution. I think I am getting something wrong.

I was going through the TRPO paper, and there was a line under Appendix D "Approximating Factored Policies with Neural Networks" in the last paragraph which I am unable to understand

The action consists of a tuple $(a_1, a_2..... , a_K)$ of integers $a_k\in\{1, 2,......,N_k\} $ and each of these components is assumed to have a categorical distribution.

I can't seem to get how each component has a categorical distribution. I think it should be the tuple that has a categorical distribution. I think I am getting something wrong.

deleted 37 characters in body
Source Link
nbro
  • 41.4k
  • 12
  • 114
  • 205

I was going through TRPO paper https://arxiv.org/pdf/1502.05477.pdfthe TRPO paper, and there was a line under Appendix D "Approximating Factored Policies with Neural Networks" in the last paragraph which I am unable to understand

"TheThe action consists of a tuple $(a_1, a_2..... , a_K)$ of integers integers $a_k\in\{1, 2,......,N_k\} $ and each of these components is assumed assumed to have a categorical distribution."

I can't seem to get how each component havehas categorical distribution. I think it should be the tuple that has a categorical distribution. I think I am getting something wrong.

I was going through TRPO paper https://arxiv.org/pdf/1502.05477.pdf and there was a line under Appendix D "Approximating Factored Policies with Neural Networks" in last paragraph which I am unable to understand

"The action consists of a tuple $(a_1, a_2..... , a_K)$ of integers $a_k\in\{1, 2,......,N_k\} $ and each of these components is assumed to have a categorical distribution."

I can't seem to get how each component have categorical distribution I think it should be the tuple has categorical distribution. I think I am getting something wrong.

I was going through the TRPO paper, and there was a line under Appendix D "Approximating Factored Policies with Neural Networks" in the last paragraph which I am unable to understand

The action consists of a tuple $(a_1, a_2..... , a_K)$ of integers $a_k\in\{1, 2,......,N_k\} $ and each of these components is assumed to have a categorical distribution.

I can't seem to get how each component has categorical distribution. I think it should be the tuple that has a categorical distribution. I think I am getting something wrong.

added 55 characters in body
Source Link
srij
  • 13
  • 4
Loading
added 126 characters in body
Source Link
srij
  • 13
  • 4
Loading
edited tags
Link
nbro
  • 41.4k
  • 12
  • 114
  • 205
Loading
edited title
Link
srij
  • 13
  • 4
Loading
Source Link
srij
  • 13
  • 4
Loading