ray/rllib/tuned_examples/ppo/pendulum-appo.yaml

22 lines
582 B
YAML

pendulum-appo-vtrace:
env: Pendulum-v0
run: APPO
stop:
episode_reward_mean: -1000 # just check it learns a bit
timesteps_total: 500000
config:
# Works for both torch and tf.
framework: tf
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