Tianshou/tianshou/core/README.md

21 lines
508 B
Markdown

# policy
YongRen
### base, stochastic
follow OnehotCategorical to write Gaussian, can be in the same file as stochastic.py
### deterministic
not sure how to write, but should at least have act() method to interact with environment
DQN should have an effective argmax_{actions}() method to use as a value network
# losses
TongzhengRen
seems to be direct python functions. Though the management of placeholders may require some discussion. also may write it in a functional form.