2020-02-24 21:18:53 -08:00
|
|
|
# Taken from rllib/tuned_examples/atari_impala_large.yaml
|
|
|
|
|
# Runs on a g3.16xl node with 5 m5.24xl workers
|
|
|
|
|
# Takes roughly 10 minutes. x10?
|
|
|
|
|
atari-impala:
|
|
|
|
|
env:
|
|
|
|
|
grid_search:
|
|
|
|
|
- BreakoutNoFrameskip-v4
|
|
|
|
|
- BeamRiderNoFrameskip-v4
|
|
|
|
|
- QbertNoFrameskip-v4
|
|
|
|
|
- SpaceInvadersNoFrameskip-v4
|
|
|
|
|
run: IMPALA
|
|
|
|
|
stop:
|
|
|
|
|
timesteps_total: 30000000
|
|
|
|
|
config:
|
2021-05-04 23:10:04 +02:00
|
|
|
num_cpus_for_driver: 0
|
2020-03-14 12:05:04 -07:00
|
|
|
rollout_fragment_length: 50
|
2020-02-24 21:18:53 -08:00
|
|
|
train_batch_size: 500
|
|
|
|
|
num_workers: 128
|
|
|
|
|
num_envs_per_worker: 5
|
|
|
|
|
clip_rewards: True
|
|
|
|
|
lr_schedule: [
|
|
|
|
|
[0, 0.0005],
|
|
|
|
|
[20000000, 0.000000000001],
|
2020-03-14 12:05:04 -07:00
|
|
|
]
|
