I create a DQNTrainer and load a checkpoint from a DQN agent that I trained. config = # loaded params.pkl config['evaluation_num_workers'] = 0 # I also tried with None, same result trainer = DQNTrainer(config=config) trainer.restore(checkpoint) trainer.config['evaluation_num_episodes'] = 1 metric…

It seems that this question was solved in this thread: [image] Cannot create R2D2 trainer with evaluation worker RLlib @fedetask , I would check what config["evaluation_config"] looks like as during evaluation this config is used. Maybe therein you get a default of 1. …

DQNTrainer evaluate() doesn't perform any episode

RLlib

avnishn March 16, 2022, 1:57am 2

It seems that this question was solved in this thread:

Topic		Replies	Views
Cannot create R2D2 trainer with evaluation worker RLlib	6	644	March 8, 2022
Evaluation worker won't stop RLlib	3	571	June 19, 2022
[RLlib] Questions about loading checkpoint and asynchrone evaluation workers RLlib	3	592	May 26, 2021
Proper way to load and evaluate trained agent RLlib	6	1581	March 4, 2022
Cannot get a simple Evaluation to work as intended RLlib	6	388	September 5, 2022

DQNTrainer evaluate() doesn't perform any episode

Related topics