2019-05-16 22:05:07 -07:00
|
|
|
pendulum-appo-vt:
|
|
|
|
env: Pendulum-v0
|
|
|
|
run: APPO
|
|
|
|
stop:
|
2019-07-29 15:02:32 -07:00
|
|
|
episode_reward_mean: -1200 # just check it learns a bit
|
2019-05-16 22:05:07 -07:00
|
|
|
timesteps_total: 500000
|
|
|
|
config:
|
2019-07-29 15:02:32 -07:00
|
|
|
vtrace: False
|
2019-05-16 22:05:07 -07:00
|
|
|
num_gpus: 0
|
|
|
|
num_workers: 1
|
2019-07-29 15:02:32 -07:00
|
|
|
lambda: 0.1
|
2019-05-16 22:05:07 -07:00
|
|
|
gamma: 0.95
|
2019-07-29 15:02:32 -07:00
|
|
|
lr: 0.0003
|
|
|
|
train_batch_size: 100
|
|
|
|
minibatch_buffer_size: 16
|
|
|
|
num_sgd_iter: 10
|
|
|
|
model:
|
|
|
|
fcnet_hiddens: [64, 64]
|
|
|
|
batch_mode: complete_episodes
|
|
|
|
observation_filter: MeanStdFilter
|