Files
ray/python/ray/rllib/tuned_examples/regression_tests/pendulum-ddpg.yaml
T

11 lines
218 B
YAML

pendulum-ddpg:
env: Pendulum-v0
run: DDPG
stop:
episode_reward_mean: -160
time_total_s: 900
config:
use_huber: True
clip_rewards: False
exploration_fraction: 0.1