Hi everyone, I am trying to distinguish the commands for ‘hyperparameter tuning of a rllib algorithm’ from the commands for ‘one-time execution of same algorithm with a constant pre-defined values of needed hyperparameters’. The page https://docs.ray.io/en/master/ray-overview/index.html#gentle-int…

@Saurabh_Arora Your understanding is correct. I’m not familiar with PopulationBasedTraining. But let’s assume there is a way to turn off hyperparam space for it. In your second link, if you use scalar values instead of tune.choice, this would turn off hyperparam space search and become just be a on…

[RLLib] Distinguishing hyperparameter tuning from single excution of RL algorithm

RLlib

Saurabh_Arora May 20, 2021, 9:29am 3

Thanks, @RickLan . I have one more related question. I posted it here: https://discuss.ray.io/t/rlllib-how-to-use-policy-learned-in-tune-run/2222

Topic		Replies	Views
Using evaluation reward from RLLIB runs on population based tuner Ray Tune stopping condition & comparisons	1	600	November 30, 2022
Tune: Some hyper parameters format are not good for search algorithm Ray Tune	2	422	November 27, 2020
Trying to set up external RL environment and having trouble RLlib	14	1395	September 28, 2021
Practical advice for RLlib hyperparameter tuning RLlib	1	378	September 12, 2022
A little help for a novice RLlib	1	374	October 26, 2022

[RLLib] Distinguishing hyperparameter tuning from single excution of RL algorithm

Related topics