ray/rllib/tuned_examples/pong-a3c-pytorch.yaml

21 lines
504 B
YAML

pong-a3c-pytorch-cnn:
env: PongDeterministic-v4
run: A3C
config:
num_workers: 16
sample_batch_size: 20
use_pytorch: true
vf_loss_coeff: 0.5
entropy_coeff: 0.01
gamma: 0.99
grad_clip: 40.0
lambda: 1.0
lr: 0.0001
observation_filter: NoFilter
model:
use_lstm: false
dim: 84
grayscale: true
zero_mean: false
optimizer:
grads_per_step: 1000