ray/rllib/tuned_examples/a3c/cartpole-a2c.yaml

11 lines
237 B
YAML

cartpole-a2c:
env: CartPole-v0
run: A2C
stop:
episode_reward_mean: 150
timesteps_total: 500000
config:
# Works for both torch and tf.
framework: tf
num_workers: 0
lr: 0.001