ray/rllib/tuned_examples/ppo/pendulum-appo.yaml
Yi Cheng fd0f967d2e
Revert "[RLlib] Move (A/DD)?PPO and IMPALA algos to algorithms dir and rename policy and trainer classes. (#25346)" (#25420)
This reverts commit e4ceae19ef.

Reverts #25346

linux://python/ray/tests:test_client_library_integration never fail before this PR.

In the CI of the reverted PR, it also fails (https://buildkite.com/ray-project/ray-builders-pr/builds/34079#01812442-c541-4145-af22-2a012655c128). So high likely it's because of this PR.

And test output failure seems related as well (https://buildkite.com/ray-project/ray-builders-branch/builds/7923#018125c2-4812-4ead-a42f-7fddb344105b)
2022-06-02 20:38:44 -07:00

22 lines
582 B
YAML

pendulum-appo-vtrace:
env: Pendulum-v1
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