Some RLlib algorithms support a LR annealing schedule via “lr_schedule”. Is there support for annealing “gamma”? If not, how should I go about implementing it? Where in the code should I start digging? Thanks!

Support for annealing gamma

RickLan May 20, 2021, 7:06am 2

Topic		Replies	Views
Learning rate annealing with tune.run() RLlib	6	1212	April 27, 2021
Change learning rete for DQN RLlib	6	523	February 25, 2022
Change params of agents Ray Tune	3	350	May 28, 2022
Ray Tune: exponential learning rate schedule on HyperOpt Ray Tune	6	1177	May 28, 2023
Very slow gradient descent on remote workers RLlib	14	2495	June 8, 2021