ray/rllib/tuned_examples/regression_tests/cartpole-ddppo.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

9 lines
202 B
YAML

cartpole-ddppo-torch:
env: CartPole-v0
run: DDPPO
stop:
episode_reward_mean: 100
timesteps_total: 100000
config:
use_pytorch: true
num_gpus_per_worker: 0