I'm new to model-based reinforcement learning and thanks for your contribution to Pytorch users.
I tried to read your code to understand the logistics of dreamerv3 but found some details are not mentioned in the original paper, especially the abbreviations of some keywords.
Hi!
I'm new to model-based reinforcement learning and thanks for your contribution to Pytorch users.
I tried to read your code to understand the logistics of dreamerv3 but found some details are not mentioned in the original paper, especially the abbreviations of some keywords.
For example,
https://github.com/NM512/dreamerv3-torch/blob/4e50f302cdfaca1c8104f203376844f82c635a4e/networks.py#L174-L179
the prev_state is a
dict
including three keys, i.e.,logit
,stoch
, anddeter
.What do they mean and where can I find a more specific explanation?
Thanks for your time!