我在自定义环境中使用 RLLib 的 PPOTrainer,我执行trainer.train()
了两次,第一次成功完成,但是当我第二次执行它时,它崩溃并出现错误:
lib/python3.7/site-packages/tensorflow_core/python/client/session.py”,第 1384 行,在 _do_call (pid=15248) raise type(e)(node_def, op, message) (pid=15248)
tensorflow.python.framework.errors_impl.InvalidArgumentError:
收到标签值 5,它超出了 [0, 5) 的有效范围。>标签值:5 5
(pid=15248) [[node default_policy/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits(定义在/tensorflow_core/python/framework/ops.py:1751)]]
这是我的代码:
主文件
ModelCatalog.register_custom_preprocessor("tree_obs_prep", TreeObsPreprocessor)
ray.init()
trainer = PPOTrainer(env=MyEnv, config={
"train_batch_size": 4000,
"model": {
"custom_preprocessor": "tree_obs_prep"
}
})
for i in range(2):
print(trainer.train())
我的环境.py
class MyEnv(rllib.env.MultiAgentEnv):
def __init__(self, env_config):
self.n_agents = 2
self.env = *CREATES ENV*
self.action_space = gym.spaces.Discrete(5)
self.observation_space = np.zeros((1, 12))
def reset(self):
self.agents_done = []
obs = self.env.reset()
return obs[0]
def step(self, action_dict):
obs, rewards, dones, infos = self.env.step(action_dict)
d = dict()
r = dict()
o = dict()
i = dict()
for i_agent in range(len(self.env.agents)):
if i_agent not in self.agents_done:
o[i_agent] = obs[i_agent]
r[i_agent] = rewards[i_agent]
d[i_agent] = dones[i_agent]
i[i_agent] = infos[i)agent]
d['__all__'] = dones['__all__']
for agent, done in dones.items():
if done and agent != '__all__':
self.agents_done.append(agent)
return o, r, d, i
我不知道是什么问题,有什么建议吗?这个错误是什么意思?