ray/rllib/tuned_examples/impala/cartpole-impala.yaml

11 lines
257 B
YAML

cartpole-impala:
env: CartPole-v0
run: IMPALA
stop:
episode_reward_mean: 150
timesteps_total: 500000
config:
# Works for both torch and tf.
framework: tf
num_gpus: 0
vtrace_drop_last_ts: false