ray/rllib/tuned_examples/regression_tests/pendulum-ddpg-tf.yaml
Sven Mika b23b6addfc
[RLlib] Stabilize Pendulum-v0 regression test cases. (#8232)
Stabilize Pendulum regression test cases.
2020-04-30 15:48:11 +02:00

10 lines
220 B
YAML

pendulum-ddpg-tf:
env: Pendulum-v0
run: DDPG
stop:
episode_reward_mean: -700
timesteps_total: 100000
config:
use_pytorch: false
use_huber: true
clip_rewards: false