Files
ray/python/ray/rllib/tuned_examples/humanoid-ppo.yaml
T
Eric Liang e4bea8d10e [rllib] Default to truncate_episodes and add some more config validators (#2967)
* update

* link it

* warn about truncation

* fix

* Update rllib-training.rst

* deprecate tests failing
2018-09-30 18:37:55 -07:00

19 lines
408 B
YAML

humanoid-ppo:
env: Humanoid-v1
run: PPO
stop:
episode_reward_mean: 6000
config:
gamma: 0.995
kl_coeff: 1.0
num_sgd_iter: 20
lr: .0001
sgd_minibatch_size: 32768
train_batch_size: 320000
model:
free_log_std: true
use_gae: false
num_workers: 64
num_gpus: 4
batch_mode: complete_episodes