ray/rllib/tuned_examples/regression_tests/pendulum-sac.yaml
Eric Liang 52cf77f5a9
[rllib] SAC no_done_at_end should default to False (#7594)
* update

* update doc

* stochastic

* cleanu
2020-03-14 11:16:54 -07:00

12 lines
328 B
YAML

pendulum-sac:
env: Pendulum-v0
run: SAC
stop:
episode_reward_mean: -300 # note that evaluation perf is higher
timesteps_total: 10000
config:
soft_horizon: True
clip_actions: False
normalize_actions: True
metrics_smoothing_episodes: 5
no_done_at_end: True