Tianshou/tianshou/optimizer/README.md

# Optimizer for policy gradient methods
TODO:

vanilla

baseline

REINFORCE

TRPO

PPO

GAE

NAF

DPG

ACKTR
TODO: policy optimizer 2017-11-06 13:50:35 +08:00			`# Optimizer for policy gradient methods`
			`TODO:`
architecture design 2017-11-06 15:15:44 +08:00
TODO: policy optimizer 2017-11-06 13:50:35 +08:00			`vanilla`
architecture design 2017-11-06 15:15:44 +08:00
			`baseline`

TODO: policy optimizer 2017-11-06 13:50:35 +08:00			`REINFORCE`
architecture design 2017-11-06 15:15:44 +08:00
TODO: policy optimizer 2017-11-06 13:50:35 +08:00			`TRPO`
architecture design 2017-11-06 15:15:44 +08:00
TODO: policy optimizer 2017-11-06 13:50:35 +08:00			`PPO`
architecture design 2017-11-06 15:15:44 +08:00
TODO: policy optimizer 2017-11-06 13:50:35 +08:00			`GAE`
architecture design 2017-11-06 15:15:44 +08:00
TODO: policy optimizer 2017-11-06 13:50:35 +08:00			`NAF`
architecture design 2017-11-06 15:15:44 +08:00
TODO: policy optimizer 2017-11-06 13:50:35 +08:00			`DPG`
architecture design 2017-11-06 15:15:44 +08:00
			`ACKTR`