2017-12-13 14:39:01 -08:00
|
|
|
pong-a3c-pytorch-cnn:
|
|
|
|
env: PongDeterministic-v4
|
|
|
|
run: A3C
|
|
|
|
config:
|
|
|
|
num_workers: 16
|
2020-03-14 12:05:04 -07:00
|
|
|
rollout_fragment_length: 20
|
2017-12-13 14:39:01 -08:00
|
|
|
use_pytorch: true
|
2017-12-30 00:24:54 -08:00
|
|
|
vf_loss_coeff: 0.5
|
2019-03-17 18:07:37 -07:00
|
|
|
entropy_coeff: 0.01
|
2017-12-30 00:24:54 -08:00
|
|
|
gamma: 0.99
|
|
|
|
grad_clip: 40.0
|
|
|
|
lambda: 1.0
|
|
|
|
lr: 0.0001
|
|
|
|
observation_filter: NoFilter
|
|
|
|
model:
|
2018-06-26 13:17:15 -07:00
|
|
|
use_lstm: false
|
2018-10-31 22:00:14 -07:00
|
|
|
dim: 84
|
2017-12-13 14:39:01 -08:00
|
|
|
grayscale: true
|
|
|
|
zero_mean: false
|
2017-12-24 12:25:13 -08:00
|
|
|
optimizer:
|
|
|
|
grads_per_step: 1000
|