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

9 lines
195 B
YAML

cartpole-ddppo:
env: CartPole-v0
run: DDPPO
stop:
episode_reward_mean: 150
timesteps_total: 100000
config:
framework: torch
num_gpus_per_worker: 0