search

jurgisp / memory-maze

Evaluating long-term memory of reinforcement learning algorithms
MIT License
129 stars 13 forks source link

How many hours and how many CPUs are needed? #8

Closed GoingMyWay closed 1 year ago

GoingMyWay commented 1 year ago

Dear authors,

It is a great repo. May I ask how many hours and how many CPUs are needed to run the experiments for each seed?

jurgisp commented 1 year ago

Hi! The best place to find those details is in the paper. This is the paragraph:

All agents were evaluated after 100 million environment steps of training. For each baseline and task, we trained five agents with different random seeds and report the average scores. A single Dreamer training run took 14 days to train using one GPU learner and 8 CPU actors. A single IMPALA training run took 20 hours to train using one GPU learner and 128 CPU actors.