mirror of
https://github.com/vale981/ray
synced 2025-03-06 18:41:40 -05:00
499ad5fbe4
- Translate all vtrace functionality to torch and added torch to the framework_iterator-loop in all existing vtrace test cases. - Add learning test cases for APPO torch (both w/ and w/o v-trace). - Add quick compilation tests for APPO (tf and torch, v-trace and no v-trace).
21 lines
551 B
YAML
21 lines
551 B
YAML
pendulum-appo-vtrace-tf:
|
|
env: Pendulum-v0
|
|
run: APPO
|
|
stop:
|
|
episode_reward_mean: -1000 # just check it learns a bit
|
|
timesteps_total: 500000
|
|
config:
|
|
use_pytorch: false
|
|
vtrace: true
|
|
num_gpus: 0
|
|
num_workers: 1
|
|
lambda: 0.1
|
|
gamma: 0.95
|
|
lr: 0.0003
|
|
train_batch_size: 100
|
|
minibatch_buffer_size: 16
|
|
num_sgd_iter: 10
|
|
model:
|
|
fcnet_hiddens: [256, 256]
|
|
batch_mode: truncate_episodes
|
|
observation_filter: MeanStdFilter
|