rl18.py

N_ITER = 40
s = "{:3d} reward {:6.2f}/{:6.2f}/{:6.2f} len {:6.2f} saved {}"

for n in range(N_ITER):
  result = agent.train()
  file_name = agent.save(CHECKPOINT_ROOT)

  print(s.format(
    n + 1,
    result["episode_reward_min"],
    result["episode_reward_mean"],
    result["episode_reward_max"],
    result["episode_len_mean"],
    file_name
   ))