Hi! I’m working with Server-Client configuration in RLlib to run a simulator as a ExternalEnv. The server side it’s running okay with a DQN algorithm. In the client side I programed a loop of episodes wich contains star_episode(), get_action(), log_returns() and end_episode() modules of the Clien…

This was solved here: [image] Ray tune not logging episode metrics with SampleBatch input RLlib Hey @Jason_Weinberg , After this gets merged, try checking out master and let me know if it works for you or if you are still missing anything.

How is your env setup? Are the rewards reported to tensorboard normally? When running the cartpole client/server examples everything works fine for me but i’m having troubles reporting rewards from my multi agent environment. I’m not using an external env though so i’d be interested to see your setu…

Hi @Blubberblub , I have no experience with multi-agent environments, but I am interested in this topic for my experiments. Perhaps I have made a mistake when saying that I programmed an ExternalEnv, because what I have really done has been to configure the server and the client, where the client ho…

'client.end_episode()' don't make any difference

RLlib

hermmanhender July 26, 2022, 5:50pm 4

This was solved here:

Topic		Replies	Views
ExternalEnv in a secuential simulator running locally? And how to register the environment RLlib	4	518	February 25, 2022
Client-Server and Tune RLlib	3	1106	June 29, 2022
Log multi agent rewards from policy_client RLlib	1	366	April 7, 2022
Ray tune not logging episode metrics with SampleBatch input RLlib	13	1293	August 9, 2022
How RLlib distinguish terminated/truncated situation in Server-client configuration? RLlib	2	369	September 14, 2023

'client.end_episode()' don't make any difference

Related topics