Example for new RLModule API with wandb callbacks

PhilippWillms August 18, 2023, 2:46pm 1

Has anyone already made experience to run PPO with new RLModule API, including checkpointing to Weights & Biases ? Would be great to share experiences!

Topic		Replies	Views
PPO - Load checkpoint from previous version fails RLlib	2	806	March 17, 2022
Proper implement of reward scaling in PPO RLlib	0	272	December 17, 2020
Hybrid Offline learning and PPO? Offline RL	3	612	May 8, 2024
Bets way to handling policy change RLlib	0	172	May 17, 2022
Saving model / policies / weights after PPO training with a custom TFModelV2 Checkpointing, Restoring	3	337	March 7, 2024

Example for new RLModule API with wandb callbacks

Related Topics