ray/rllib/tuned_examples/dqn/cartpole-dqn.yaml
Eric Liang af8a93f2a4
Deflake some RLlib tests (#14947)
* fix

* update

* 100

* flake
2021-03-26 11:45:17 -07:00

13 lines
298 B
YAML

cartpole-dqn:
env: CartPole-v0
run: DQN
stop:
episode_reward_mean: 100
timesteps_total: 100000
config:
# Works for both torch and tf.
framework: tf
model:
fcnet_hiddens: [64]
fcnet_activation: linear
n_step: 3