search

markkho / msdm

Models of Sequential Decision-Making
MIT License
44 stars 6 forks source link

Softmax policy #53

Closed markkho closed 2 years ago

markkho commented 2 years ago

This line should not be softmaxdistribution but rather dictdistribution

https://github.com/markkho/msdm/blob/3922b7ee1eaa7cd587207616a83d2f8b62a60f0b/msdm/core/problemclasses/mdp/policy/tabularpolicy.py#L52

markkho commented 2 years ago

Fixed in 1bcba01fc06c4993c5d9b34f707a0e6041f27874