hongshaorou/Tianshou

History

Haosheng Zou 6611d948dd add value_function (critic). value_function and policy not finished yet.

2017-12-22 00:22:23 +08:00

..

0. code refactor, try to merge Go and GoEnv

2017-12-16 23:29:11 +08:00

add value_function (critic). value_function and policy not finished yet.

2017-12-22 00:22:23 +08:00

add value_function (critic). value_function and policy not finished yet.

2017-12-22 00:22:23 +08:00

__init__.py

mcts update

2017-11-17 15:09:07 +08:00

losses.py

finished very naive dqn: changed the interface of replay buffer by adding collect and next_batch, but still need refactoring; added implementation of dqn.py, but still need to consider the interface to make it more extensive; slightly refactored the code style of the codebase; more comments and todos will be in the next commit

2017-12-17 12:52:00 +08:00

README.md

implement dqn loss and dpg loss, add TODO for separate actor and critic

2017-12-15 14:24:08 +08:00

README.md

#TODO:

Separate actor and critic. (Important, we need to focus on that recently)

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

referencing QValuePolicy in base.py, should have at least the listed methods.

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.