2017-11-04 01:38:59 +08:00
|
|
|
# tianshou
|
|
|
|
Tianshou(天授) is a reinforcement learning platform.
|
2017-11-06 15:58:21 +08:00
|
|
|
|
|
|
|

|
|
|
|
|
2017-11-06 15:17:55 +08:00
|
|
|
## data
|
|
|
|
TODO:
|
|
|
|
|
|
|
|
Replay Memory
|
|
|
|
|
|
|
|
Multiple wirter/reader
|
|
|
|
|
|
|
|
Importance sampling
|
|
|
|
|
|
|
|
## simulator
|
|
|
|
go(for AlphaGo)
|
|
|
|
|
|
|
|
## environment
|
|
|
|
gym
|
|
|
|
|
|
|
|
## core
|
|
|
|
TODO:
|
|
|
|
|
|
|
|
Optimizer
|
|
|
|
|
|
|
|
MCTS
|
|
|
|
|
|
|
|
## agent (optional)
|
|
|
|
|
|
|
|
DQNAgent etc.
|