考虑以下示例:
特别是以下代码:
# Train
for i in range(iterations):
train_results = train_agent.train()
if i % 2 == 0 or i == iterations - 1:
checkpoint = train_agent.save(tune.get_trial_dir())
tune.report(**train_results)
train_agent.stop()
是否可以在每次迭代后渲染环境?